Façade Psychology Is Hardwired: AI Selects Windows Supporting Health

Abstract

This study uses generative AI to investigate the influence of building façade geometry on human physiological and psychological health. Employing Christopher Alexander’s fifteen fundamental properties of living geometry and a set of ten emotional descriptors {beauty, calmness, coherence, comfort, empathy, intimacy, reassurance, relaxation, visual pleasure, well-being} in separate tests, ChatGPT 4.5 evaluates simple, contrasting window designs. AI analyses strongly and consistently prefer traditional window geometries, characterized by symmetrical arrangements and coherent visual structure, over fragmented or minimalist–modernist alternatives. These results suggest human cognitive–emotional responses to architectural forms are hardwired through evolution, privileging specific geometric patterns. Finally, ChatGPT o3 formulates ten detailed geometric rules for empathetic window design and composition. It then applies these criteria to select contemporary window typologies that generate the highest anxiety. The seven most anxiety-inducing designs are the most favored today worldwide. The findings challenge contemporary architectural preferences and standard window archetypes by emphasizing the significance of empathetic and health-promoting façade designs. Given the general suspicion among many readers of the frequently manipulative and unreliable use of AI, its use in this experiment is not to validate design decisions directly, which would put into question what the AI is trained with, but to prove a correlation between two established methodologies for evaluating a design. AI is used as an analytical tool to show that Alexander’s geometric rules (the guidelines proposed beforehand) closely match emotional reactions (the desirable outcomes observed afterward). This novel use of AI suggests integrating neurodesign principles into architectural education and practice to prioritize urban vitality through psychological well-being.

1. Introduction

1.1. Building Façades Influence Human Psychological Health—Use ChatGPT to Find out How

The external appearance of buildings communicates distinct and specific architectural styles that define the built environment. Urban regions covering immense areas around the world shape people’s psychological states, by influencing the neurological reactions of everyone who experiences them. And yet, standard design thinking posits—erroneously, as this paper suggests—that defining the visual urban environment is entirely the privilege of the individual architect. In fact, the effect of urban information on the human body is immense and it influences human health in both the short and long terms [1,2,3,4,5,6,7,8,9,10,11]. Collectively, those studies provide strong evidence that biophilic design and human-centered geometries improve cognitive function, emotional well-being, and psychological comfort, advocating design practices rooted in evolutionary biology and innate human responses.

It follows that a major responsibility for a design, especially from those individuals who approve it before building, is to make sure that no harm is done to a city’s users. While there are strict guidelines in place for the more obvious physical dangers to public health, unconscious psychological effects of the façade’s design are so far neglected. For this reason, architectural culture and the public encourage artistic innovation without any constraints. Indeed, departures from design precedents are celebrated by architects without ever thinking about the possibly negative consequences of their choices.

The basic components of geometry act directly, though unconsciously, to affect the bodily and mental state of a user. Cognitive and neuromuscular functions are therefore shaped by the visual environment in which a person finds him/herself immersed. Alarmingly, an extensive 20th century design tradition seems to privilege geometrical elements that generate anxiety. ChatGPT identifies the seven most prevalent contemporary window typologies as being the most anxiety-inducing. This fact tends to be ignored while the public focuses on other aspects of design. Investigating health effects of the visual exposure to building façades should become a priority in multidisciplinary research.

Applying the AI large-language model ChatGPT has led to multiple breakthroughs in the medical field [12,13,14,15], with progress accelerating. Architecture is lagging behind in this respect while it concentrates on using graphical AI to generate fantastical new designs. A notable exception is Jurisevic et al., who apply ChatGPT to evaluate the energy efficiency of kindergartens [16,17]. This task turns out to be complex, as ChatGPT had to collect technical data on buildings and discover regulations covering a 100-year period. It did this remarkably well, with its results competing with expert human opinion. The present study on window shapes exploits ChatGPT’s ability to assemble and synthesize data, together with its analytical skills. This synthesis at the intersection of architecture, mathematics, and psychology would be impossible without artificial intelligence. ChatGPT gathers findings from qualitative and quantitative research on how architecture users respond to the environment. Scientific research generates validated data that are available for the model to draw upon. A particular approach to thinking about architecture employs innovative interdisciplinary approaches that seek to discover optimal design solutions. As a secondary effect, arguments from the natural sciences and psychology rehabilitate traditional architectural morphology and building techniques.

By utilizing ChatGPT to simulate cognitive functions, this paper creates a computational model and experimental platform for aspects of the mind. Generative AI can manipulate architectural variables and environmental inputs and observe the functional outcomes. It thus becomes an indispensable tool for exploring lived experience. AI’s transformative potential lies in uncovering the sensory basis of architecture.

1.2. Christopher Alexander’s Fifteen Fundamental Properties of Living Geometry

Living geometry is defined by a set of descriptors including coherence, fractal scaling, harmony, nested symmetries, and visual balance [18,19,20,21]. People instinctively “know” living geometry (though they may not be aware of the actual term), so any study of design preferences must take this into account. The human body responds positively to living geometry, indicating that people’s preferences are set to it, and the body’s reactions are unconsciously activated by its presence. Subjective “likes and dislikes” accumulate on top of hard-wired responses based on living geometry, which can be submerged but never erased.

Generative AI already knows the 15 fundamental properties—since it accurately describes them when asked—listed as follows:

• Levels of scale;
• Strong centers;
• Thick boundaries;
• Alternating repetition;
• Positive space;
• Good shape;
• Local symmetries;
• Deep interlock and ambiguity;
• Contrast;
• Gradients;
• Roughness;
• Echoes;
• The void;
• Simplicity and inner calm;
• Not-separateness.

The AI experiment described below demonstrates a strong coincidence between window designs that have a positive emotional effect on their users and window designs that follow Christopher Alexander’s 15 properties of living geometry. Implementing AI to evaluate a series of window designs using both these sets of criteria shows that Alexander’s 15 properties provide a reliable predictor and design guideline for windows that impact their users positively. Since emotional effects can typically be measured only after the fact, this experiment suggests that implementing Alexander’s 15 properties during the design phase provides a reliable methodology for achieving designs that will have a positive emotional effect.

Furthermore, the paper’s methodology in employing AI indicates that its conclusion is not a matter of personal preference but an expression of the large body of neurological knowledge embedded in the AI database about human emotional responses to the physical environment. Consequently, an added value of this paper is to provide a guideline for using AI for similar experiments that would help in determining design approaches that support the well-being of their users.

The 15 geometric properties are best used together with a large-language model by uploading a more extensive description, included here as a Supplementary File at the end of this paper. A useful approach is to investigate the existence of “living geometry” as a set of design and tectonic principles by discovering how far it is represented in each built example. Similar methods are used by Bin Jiang [22], Danny Raede [23], and the present author [21]. Testing for the 15 properties provides an objective measure of how far a structure satisfies a specific set of geometric criteria. This paper will establish that the human body preferentially seeks out these 15 properties to maintain its health and well-being.

1.3. AI Preferences Based on Ten Emotional Indicators

Having brought the issue of how environmental geometry affects the human body to general attention, many new techniques of gathering data are available to settle this question today. Those include portable physiological sensors, portable eye-tracking devices, and emotional responses from both real and virtual environments [24,25,26,27,28,29,30,31,32,33,34]. These references provide empirical evidence gathered using both physiological sensor technologies and psychological surveys, showing measurable effects of architectural environments on cognitive responses, emotional reactions, human behavior, and stress levels. They underline the value of employing biometric methods for objectively assessing human interactions with building façades and interior environments.

Sensors consistently measure the psycho-physiological effect of different building façades on the people experiencing them. This facilitates the correlation of sets of geometrical and other qualities with health enhancement and also identifies qualities that have the opposite effect. Designers can extract guidelines from exhaustive surveys for improving public health through the sensitive design of the external built environment.

While other studies actively measure user responses to building façades, this paper applies generative AI large-language models to study the effect. AI takes the place of an enormous pool of subjects who could be asked for their façade preferences. The advantages of using AI are many: there is no need to employ a group of individuals; results are immediate; the volume of information accessed by large-language models far exceeds most practical surveys of people. There are, of course, technical questions to consider so that AI surveys are accurate enough to take seriously, and those problems are discussed here.

The world’s stored knowledge to which AI has access is mined for people’s preferences in building façades. Such an exercise must resolve the problem of subjective taste and personal opinion. Innate preferences depend upon emotional feedback from what is being experienced. One cannot simply ask a subject what they “like” but has to come up with the right questions that dig deeper into unconscious bodily responses. Those have been hard-wired by human evolution to help guarantee survival.

ChatGPT draws upon open-source participant data. The model’s preference profiles match a large body of biometric and eye-tracking studies already conducted. Because the goal is to test whether a large-language model can replicate known human preferences from the open-access literature, ChatGPT serves as a text-analytic interface to the vast, peer-reviewed body of empirical work on visual perception that is embedded in its training data. When prompted, the model retrieves and synthesizes thousands of pre-existing, sensor-based findings that have already been validated by independent studies with human participants.

One way to circumvent subjectivity is by asking a large-language program to evaluate ten distinct emotional qualities perceived in a building’s façade. This approach is totally different from evaluating geometrical qualities such as Alexander’s 15 fundamental properties. While each emotional quality could be influenced by prior learning, with some more so than others, it is conjectured that their totality provides a largely objective measure. Intuitively, the subjective component of each quality may be canceled by the collective objectivity of all the others in the group.

While this ambiguity is especially true of “beauty”, several authors are investigating the biological basis for beauty [35,36,37,38,39] with promising results. That set of articles explores the biological and theoretical foundations underlying human perceptions of beauty and emotional coherence in architecture. They suggest that architectural beauty has a measurable neurological and evolutionary basis, indicating that very specific geometric qualities elicit positive emotional responses that are universal among the population.

Below is a set of ten proposed qualities (“beauty–emotion cluster”) that elicit a positive-valence feeling from experiencing a built structure, and which are used in the present investigation:

• beauty;
• calmness;
• coherence;
• comfort;
• empathy;
• intimacy;
• reassurance;
• relaxation;
• visual pleasure;
• well-being.

These ten inherent and observable qualities are based on objective psychological responses from a person’s body. The properties are specific enough to use generative AI in testing images for emotional cues. Other possible visual factors may draw attention and fascination, but not in an unambiguously positive manner, so they are not included in the above list. The present experiment deliberately departs from a direct mathematical analysis of living geometry, to instead rely strictly on emotional and psychological responses. Combining the above ten qualities is expected to offer a useful evaluation for the purposes of AI prompting.

Emotions help to gauge reactions to gravity, a measure missing from the 15 fundamental properties. The body reacts strongly yet unconsciously to balanced or unbalanced standing structures. Façade design triggers human gravitational perception—visual stability through vertical symmetry, and the size of architectural elements diminishing with increasing height—and pre-modernist windows obey these rules. Violating these expectations generates unease. Combining Alexander’s 15 fundamental properties with the 10 emotional descriptors yields a more holistic tool for assessing façade coherence.

Two distinct AI experiments are described here: (i) Evaluating window designs in a building’s façade to gauge the presence of living geometry. The first test is achieved using Christopher Alexander’s Fifteen Fundamental Properties as a convenient and practical measure for living geometry. Those 15 geometrical descriptors combine to define living geometry represented in any design, façade, or setting. (ii) Supporting those findings by performing an independent evaluation, using an AI large-language model, for the above 10 emotional descriptors. The results from these two independent AI experiments turn out to agree completely. Traditional composition and window design are consistently selected. The goal of proving that emotional responses correlate directly with mathematical content is thereby achieved.

Generative AI matches textual cues to predefined criteria. AI-generated evaluations may introduce interpretative biases, as outcomes depend on textual descriptions rather than direct visual input. Consequently, the lack of direct sensory processing cannot capture subtle visual nuances and contextual details that influence human perceptions. Large-language models inherently lack visual intelligence, yet similar conclusions are supported by independent biometric and neurological studies reflective of documented human preferences. This AI tool is therefore judged accurate enough for the present “proof of principle” analysis.

The second part of this paper applies ChatGPT to derive new results by iteration. In Section 6, ChatGPT is asked for a detailed set of rules that establish a generative grammar for window composition and design based on the two AI experiments. ChatGPT comes up with ten evidence-based rules for “empathetic” windows. AI uses the first part of this paper as a framework to attach open-access findings from psychobiology and building-science about human responses to window form. The detailed list of rules looks like it could derive from traditional architecture, but it comes instead from qualitative heuristics and human psychology.

Utilizing a feedback loop to derive more results is a cornerstone of modern AI development. In a second iteration, ChatGPT uses this paper together with the ten evidence-based rules for “empathetic” windows as a diagnostic tool (Section 7). AI-based analysis based on the present model selects those window typologies that generate the most anxiety in a viewer. Those cases of inadequate emotional response describe popular standard industrial and “cutting-edge” window designs—a finding that is alarming.

1.4. Comparing Pairs of Visuals

This paper applies the method of pairwise comparison to evaluate window shape and positioning. Which one of a pair of similar examples generates a greater positive feeling as a result of embodying the above ten qualities? Such a relative question is easier to answer than a direct evaluation of each individual quality, which necessitates an absolute estimate of how intensely that particular quality is perceived. In that case, one has to judge whether a quality is present or not; or make a comparative judgment on a Likert scale of 1 to 5, or 1 to 10. That involves more work.

Christopher Alexander faced the same problem of measuring qualities responsible for living structure (which includes living geometry plus other relevant factors such as color, etc.). His solution was to resort to pairwise comparisons in what he terms the “Mirror of the Self Test” [18] (Chapter 8). This practical method proved successful and has inspired pairwise evaluations of buildings using eye-tracking simulation software [40,41,42,43]. It is now standard procedure to visually scan a pair of images and determine where the eye is attracted during the first 3 s, when initial eye movements are informed by pre-attentive (unconscious) visual processing happening in the first 200 ms after image presentation.

Comparing similar pairs of window compositions through a large-language model derives a consistent set of design criteria. These AI experiments select designs that obey living geometry, without having been programmed to do so. The results identify more traditional design styles as better suited to human health and well-being indirectly, arising from AI independently of explicit empirical data such as stress indicators, eye-tracking, or neural responses. The causality is that ChatGPT first discovers healthier window typologies; then it is noticed that those resemble traditional designs, not the other way round. The evidence lies in the model retrieving and synthesizing thousands of pre-existing, sensor-based findings that have already been validated by independent laboratories with human participants. This suggests that future window design should incorporate older templates to be perceived as emotionally and psychologically comfortable. Otherwise, a person looking at a façade will see it as an alien structure.

1.5. Controversial and Diverging Hypotheses

This paper’s results turned out to be controversial. First, the standard design toolkit for windows on a building’s façade is questioned as being non-optimal for human psychological health. Second, the professional motives that lead architects to apply standard typologies are also put into doubt. Without being programmed to do so, generative AI resurrects the controversy of opposing tastes between architecture professionals and the public. Up until now, contemporary society and the decision-making groups that determine what gets built on a large scale favor the tastes of trained architects. This trend continues despite strong and vociferous opposition from the public.

It has been common practice to frame this debate as occurring between “experts” and “novices”; but it is now time to abandon those labels [44,45,46,47]. The reason is that an expert opinion is normally given more weight than the opinion of a novice, yet how can we value an architectural expert whose opinions contradict human physiology? Such conditioned beliefs are entirely subjective and, moreover, could harm human health. A new evaluation of expert knowledge on the effects of architectural form comes from scientific data [48,49,50,51]. Today, the accepted narrative as taught in the schools is never exposed to verification and is validated instead by tacit messages [52,53,54,55].

Other authors have measured electroencephalograms (EEGs) of subjects viewing images of windows of different shapes [56]. A clear distinction emerged between “pleasant” and “unpleasant” sets of windows: the first comprised rounded and rectangular ones, whereas the second set had triangular but vertically symmetric features. (Some award-winning buildings prominently feature sharp triangular doors or windows.) Although the intent is the same as in the present paper, that experiment did not attempt to gauge reactions to diagonal or unbalanced windows.

Recent developments in neuroarchitecture shed light on these and related questions by applying the scientific method to obtain data [57,58,59,60]. Dominant architectural culture continues to focus on style-based narratives, however. Nobody mentions the uneasiness felt from sharp (acute isosceles) triangles versus the emotional comfort from traditional window compositions. Architecture schools still train students to design sterile, minimalist environments, dismissing user-centric esthetics as “non-architectural”.

The literature and media unfortunately prejudice opposite opinions on how to design building façades. This makes an analysis of reactions to different façades unnecessarily problematic. Ordinary people react spontaneously through their body’s evolved biological responses. Labeling as “novices” people with unsullied neurological sensitivity biases and skews the situation. Labeling individuals who diverge from the biological basis of beauty because their training suppresses human neurological responses as “experts” endows them with an undeserved authority. Those “experts” falsely condemn natural reactions to buildings as due to ignorance.

Architects misinterpret these results to fit the dominant narrative, claiming it is not surprising that AI asking common people (without architectural training) for their choices in window composition gives back traditional typologies. Yet the AI did not ask for preferences. Instead, AI discovers two independent and parallel results: (i) living geometry corresponds to traditional designs; and (ii) traditional designs give positive-valence emotional feedback. These are empirical findings and not opinions.

1.6. Embracing Empathetic Design

The beauty–emotion cluster {beauty, calmness, coherence, comfort, empathy, intimacy, reassurance, relaxation, visual pleasure, well-being} represents mutually reinforcing states, not ten isolated labels. People rarely report these as separate feelings. The ten terms describe partially overlapping facets of a single state triggered by living geometry. Feedback loops (e.g., feeling safe heightens sensitivity to beauty) implement interrelationships. The ten emotional properties form a tightly knit affective (mood) network that environmental geometry either supports or disrupts [61,62,63,64,65].

The present AI experiments are driven by the conviction that the built environment ought to enhance the user’s psychological well-being. Empathetic design prioritizes cognitive and emotional reactions as key factors to improving the urban realm. Nevertheless, this goal competes with common motivations in contemporary practice such as pursuing fashionable trends (without evaluating their impact), selecting design archetypes tied to ideologies, continuing an industry standard, extracting profit while overriding other concerns, and minimizing construction costs.

Product design adopts empathetic design principles [66,67,68]. With “empathy-centered architecture”, the physical structure triggers positive responses in a user. Focusing on user experience (UX) and emotional well-being boosts the market success of a product. Adaptations go beyond ergonomic considerations, to consider the subtle emotional state of the user involving nonverbal clues. Understanding and anticipating user reactions improves product design through feedback and iterations. User-centered design is based on data [69,70,71,72].

Mainstream architects pay little attention to empathy-driven design that generates emotionally responsive architecture. Few practitioners utilize knowledge of how people react unconsciously when viewing a building. Researchers in fields outside architecture are undertaking experiments that diagnose buildings for their empathetic qualities [73,74,75]. Confusingly, recent industrial–minimalist buildings are labeled as empathetic (using “empathetic” as a buzzword) even though they are not. They assert empathy through a narrative of social inclusion, not by measured occupant emotion.

1.7. Attractive, Engaging Façades Are the Key to the Lively Pedestrian City

As argued by Christopher Alexander and Jan Gehl, the heart of the city must encourage pedestrian use. To do so, the façades surrounding and defining urban spaces must offer informational interest and positive-valence emotional feedback. Otherwise, no pedestrian wishes to occupy that open space; and will either avoid it or traverse it as quickly as possible.

The informational content of urban space has been treated in depth in the literature [76,77,78,79,80,81,82,83]. These references collect established principles and evidence-based design patterns that enhance human experience in urban environments. They emphasize how façade compositions and spatial configurations directly influence pedestrian behavior, comfort, emotional responses, and social interactions—key aspects central to this paper’s argument on empathetic, neurologically grounded architectural design. The attractiveness of the enveloping façades plays a crucial role in the success of the urban space itself. This goes for urban plazas just as much as ordinary streets.

Bringing in generative AI as an investigative tool opens up interesting possibilities for further research. The results derived in this paper go beyond the simple esthetics of building façades, by contributing in a major way to how a city defines its pedestrian realm. People feel that they belong to a city only if they connect emotionally with its façades [84,85,86,87]. Obsessed with efficiency, engineering, materials, and tectonics, architects and planners apparently forgot this necessary mechanism. The profession does not yet prioritize a basic aspect of design that cooperates with urbanism to improve how cities work.

2. ChatGPT Evaluates Window Preferences Using the Properties of Living Geometry

The goal here is to evaluate the visual impact of experiencing windows on a building’s façade from the outside. This study is not concerned with the view through a window from the inside. Ten line drawings of window designs and alignments in a façade were prepared to illustrate the simplest geometrical features through contrasting pairs. Each pair was presented to ChatGPT 4.5 for evaluation using Christopher Alexander’s 15 fundamental properties (with an uploaded list given in the “Supplementary Materials” at the end of this paper). Figure 1, Figure 2, Figure 3, Figure 4, Figure 5, Figure 6, Figure 7, Figure 8, Figure 9 and Figure 10 below were used in this AI experiment.

There is a sound mathematical reason for choosing only a small number of very simple line drawings for this analysis: to identify the geometrical primitives responsible for the most important effects. Everything else follows from that baseline. But that discussion is best left for after the derivation of the ten evidence-based rules for “empathetic” windows in Section 6.

ChatGPT’s answer for this experiment is reproduced below for the specific instance of Figure 1. The text details how the software deals with the question.

Prompt to ChatGPT 4.5: “Use the uploaded list of Christopher Alexander’s 15 properties to evaluate the comparative degree of living geometry in the attached pair of figures. Find how each property is present in the figure on the LHS compared to the RHS figure, and note which side wins. Then give the result as a double sum (m, n) for the respective counts of properties: m = total for the winning properties for the LHS, and n = total for the winning properties for the RHS”.

ChatGPT 4.5: “Based on the detailed description of Christopher Alexander’s 15 fundamental properties, the comparative evaluation of the attached pairs of figures yields the following results. Pair shown in Figure 1:

• Levels of Scale. LHS: Not clearly present. RHS: Not clearly present. Winner: Neither.
• Strong Centers. LHS: Disrupted and weak. RHS: Clearly defined by symmetrical windows (strongly present). Winner: RHS.
• Thick Boundaries. LHS: Thin boundaries. RHS: Thin boundaries. Winner: Neither.
• Alternating Repetition. LHS: Irregular openings, weak. RHS: Simple repetition, no clear alternation. Winner: Neither.
• Positive Space. LHS: Fragmented and incoherent. RHS: Clearly coherent (strongly present). Winner: RHS.
• Good Shape. LHS: Irregular and fragmented. RHS: Clearly coherent and symmetrical (strongly present). Winner: RHS.
• Local Symmetries. LHS: Clearly broken. RHS: Clearly symmetrical (strongly present). Winner: RHS.
• Deep Interlock and Ambiguity. LHS: Weakly present. RHS: Simple form, no interlock. Winner: Neither.
• Contrast. LHS: Asymmetric and clashing (not strong). RHS: Minimal contrast. Winner: Neither.
• Gradients. LHS: Not present. RHS: Not present. Winner: Neither.
• Roughness (informal coherent repetition). LHS: Informal but irregular and asymmetric (thus weak). RHS: Informal coherent lines (strongly present). Winner: RHS.
• Echoes. LHS: No echoes. RHS: Simple echoes present in vertical shapes (weak). Winner: Neither (weak).
• The Void. LHS: No coherent void. RHS: Simple central void slightly present (weak). Winner: Neither.
• Simplicity and Inner Calm. LHS: Disrupted, fragmented. RHS: Clearly calm and coherent (strongly present). Winner: RHS.
• Not-Separateness. LHS: Elements fragmented and separate. RHS: Connected and coherent (strongly present). Winner: RHS.

Results: LHS: 0 total. RHS clearly wins: properties (2, 5, 6, 7, 11, 14, 15) = 7 total.

Final result: (LHS, RHS) = (0, 7)”.

These results reflect significant differences in living geometry between the two sides in each pair, as per the definitions of Christopher Alexander’s 15 properties. They are surprisingly accurate, given the deliberate simplicity of the figures. The 15 properties were meant to analyze coherent complexity in artifacts and structures, which these rough sketches hardly possess. The total counts for all the 10 figures are listed in

Table 1. Comparative evaluation of pairs of window designs in a façade using Christopher Alexander’s 15 fundamental properties of living geometry. The totals indicate how many properties are strongly present in each façade of the pair (Left-Hand Side—LHS vs. Right-Hand Side—RHS), clearly showing the consistent top-scoring of designs on the RHS across all ten figures.

Figure No.	Geometry—LHS Score	Geometry—RHS Score
1	0	7
2	2	6
3	0	6
4	1	6
5	1	7
6	1	6
7	0	7
8	2	7
9	0	7
10	0	7

.

Generative AI can choose from a pair of similar images according to criteria stated in the prompt. Using large-language models to carry out substantive research offers an opportunity for anyone wishing to undertake such a project. There is no overhead; results are immediate; the experiments can be adjusted on the fly; the investigation can become an iterative procedure using feedback to improve accuracy. Just as important, everyone can very easily check another group’s results and replicate their data. The only factor of concern is to use the correct prompt engineering, an art that is only now being developed.

A final note on the figures. When conducting visual surveys with human subjects, especially in choosing between a pair of similar figures, the experimenters must usually account for left–right bias. This effect is due to reading from left to right in the West [88]. Mitigating any inherent L-R bias can be accomplished by switching some of the pairs so that the “better” choice is not consistently on the RHS, as it is here. However, as these figures were processed by a large-language model, it was not felt necessary to resort to any tricks to avoid inherent bias that is a specifically human factor.

3. ChatGPT Evaluates Window Preferences from Ten Emotional Responses

A second AI experiment was performed with the goal of introducing an emotion-based tool (the beauty–emotion cluster) for judging the windows in the 10 figures. The separate results coming from emotion and from geometry can then be compared.

Prompt to ChatGPT 4.5: “Now do a different measurement of the same 10 figures in the already attached paper using 10 cognitive-emotional criteria. Evaluate the window arrangements in each pair shown in Figure 1, Figure 2, Figure 3, Figure 4, Figure 5, Figure 6, Figure 7, Figure 8, Figure 9 and Figure 10 to compare probable cognitive and emotional responses. Do this independently for the following ten criteria. Which one of the pair generates a greater feeling of beauty; calmness; coherence; comfort; empathy; intimacy; reassurance; relaxation; visual pleasure; well–being. Present the results as a pair of numbers (LHS, RHS) where LHS is the sum total of the preferences for the left figure, and RHS is the sum total of the preferences for the right figure. Give me a table of the final sums, and one detailed description of the analysis for Figure 1 only”.

ChatGPT 4.5: “Here is the detailed analysis for Figure 1, based on the ten cognitive-emotional criteria. Cognitive-Emotional Evaluation (LHS vs. RHS).

• Beauty: The RHS is symmetrical and balanced, strongly preferred for beauty. (RHS wins).
• Calmness: The RHS’s symmetry induces calmness; the LHS appears fragmented and stressful. (RHS wins).
• Coherence: RHS clearly presents coherent geometry; LHS is irregular and lacks coherence. (RHS wins).
• Comfort: RHS offers visual stability and predictability, which is comforting. (RHS wins).
• Empathy: RHS’s harmonious form fosters a feeling of empathy; LHS does not. (RHS wins).
• Intimacy: RHS symmetrical windows suggest intimacy and human scale; LHS does not. (RHS wins).
• Reassurance: RHS symmetry and order reassure viewers; LHS arrangement creates unease. (RHS wins).
• Relaxation: The symmetry of the RHS strongly promotes relaxation; LHS disrupts relaxation. (RHS wins).
• Visual Pleasure: RHS’s well-organized form provides visual pleasure; LHS feels visually unpleasant. (RHS wins).
• Well-being: RHS aligns with perceptions of balance and psychological comfort; LHS negatively impacts sense of well-being. (RHS wins).

Total for Figure 1 (Cognitive-Emotional Criteria): LHS = 0, RHS = 10”.

The results of analyzing all 10 figures are listed in

Table 2. Comparative evaluation of pairs of façade window designs using responses to the ten emotional qualities. The totals indicate how many properties are strongly present in each façade of the pair (Left-Hand Side—LHS vs. Right-Hand Side—RHS). The comparative totals indicate the number of positive emotional responses (beauty, calmness, coherence, comfort, empathy, intimacy, reassurance, relaxation, visual pleasure, well-being) clearly favoring the right-hand side (RHS) window arrangements across all ten figures.

Figure No.	Emotion—LHS Score	Emotion—RHS Score
1	0	10
2	2	8
3	0	10
4	1	9
5	1	9
6	1	9
7	0	10
8	2	8
9	0	10
10	0	10

. This evaluation tool is even simpler to use, since the 10 emotional responses upon which it is based do not need to be explained to the software. ChatGPT draws upon a vast databank documenting human responses to visual patterns. It is worth remarking that, because of the sheer numbers involved, popular opinion overwhelms by far any possibly biased responses due to architectural conditioning.

4. Results: Emotional Preferences Correspond to Geometrical Qualities in Window Design and Positioning

The results from ChatGPT 4.5 evaluating the ten figures using geometry are listed in Table 1. Both AI methods consistently selected the more traditional composition or design shown on the RHS in every pair of window sketches (Figure 1, Figure 2, Figure 3, Figure 4, Figure 5, Figure 6, Figure 7, Figure 8, Figure 9 and Figure 10). This compelling result is confirmed and reinforced by the coincidence of the two independent approaches to analyzing the problem.

These results are compared to the separate evaluations of the 10 figures using the emotion-based prompt of the beauty–emotion cluster, listed in Table 2.

The coincidence of values in the columns for the LHS scores in both Table 1 and Table 2 is not a misprint. It is curious to discover that the emotional evaluation of the 10 simple figures somehow seems more robust than when performed using the geometrical criteria. The model gains explanatory and predictive strengths by combining the geometric with the emotional evaluations, shown as a graph in Figure 11 below.

The experimental conclusions are that, overwhelmingly, the more traditional (i.e., geometrically coherent) pair of windows in each of the figures scores higher. Those are represented by the RHS figures in all cases. Since the two distinct AI experiments reinforce each other, these results cannot be dismissed as some artifact of the software or opinion of the author.

5. Discussion: The Body Is Hard-Wired to Seek Specific Patterns in the Visual Environment for Survival

This paper applied the large-language model ChatGPT to determine how the geometry of building façades—specifically, window design and composition—affects users. In what amounts to a pilot study, even the simplest variations turn out to influence design choices. The fact that the drawings used for analysis are somewhat abstracted, and do not directly correspond to images that could be found on the web, makes the results all the more valuable. Adaptive design that promotes cognitive and psychological health must take these findings seriously.

Readers may reasonably question how ChatGPT, being fundamentally a text-based model, can determine emotional feedback defined by the set of ten descriptors {beauty, calmness, coherence, comfort, empathy, intimacy, reassurance, relaxation, visual pleasure, and well-being}. A large-language model operates by predicting textual responses based on statistical patterns derived from extensive training on vast datasets. The data base encompasses multiple sources of written material. ChatGPT’s assessments of emotional descriptors do not originate from direct sensory experiences, but rather from documented language patterns describing human emotional responses.

This tool has clear limitations. Unlike direct neurological or physiological measurements—such as biometric sensors or eye-tracking studies, which register emotional and physiological states—ChatGPT’s emotional evaluations are secondhand abstractions. Ideally, therefore, these AI-generated estimations for the beauty–emotion cluster should be complemented by empirical validation.

Summarizing these findings leads to understandings in the list below:

• ChatGPT turns out to be very useful in evaluating window design and placement using either emotional or geometrical criteria.
• Results from emotional choices turn out to agree remarkably well with choices using the elements of living geometry.
• Both AI-based assessments consistently pick out the traditional compositions and window designs in every case examined here.
• Referring to work by other authors, large-language models are unexpectedly successful in discovering general human preferences.
• Architects are trained to privilege designs that were revealed as non-optimal for cognitive and psychological health.
• The ten emotional criteria introduced here turn out to be very efficient when combined into a diagnostic tool for healthy design.

What is remarkable is the consistency of choices, which uncovers a profound split with what the architectural industry is giving us. A survey of standard window typologies reveals that the building and construction industries have settled on mass-producing archetypes that fail the present tests. And yet nobody seems to raise the issue, as societies the world over accept these window designs without questioning them. It is difficult to explain this phenomenon taking place in a market-driven economy except by reference to a mass movement.

The two complementary, mutually reinforcing AI assessments are best used together. There is an important aspect in the emotional evaluation—human neurological anchoring in gravity—that the geometrical evaluation using the 15 fundamental properties misses. While gravitational perception effects may not be relevant when analyzing artifacts and plans of buildings or urban spaces, those are crucial for façade composition. People instinctively seek confirmation of gravitational stability in their surroundings through the vertical orientation of standing structures, according to two specific visual needs.

First, perceiving a vertical symmetry axis provides essential stability. Any deviation from bilateral gravitational symmetry, as illustrated by the asymmetrical arrangement in Figure 1 (LHS), generates neurological discomfort and a sense of visual instability. Second, architectural elements, particularly windowpanes and vertically aligned windows, are psychologically expected to diminish in size with increasing height. Placing visually lighter elements above heavier/larger ones mirrors gravitational stability, which creates a comforting illusion. Violating this progression in Figure 8 (LHS) leads to perceptual unease and a subconscious rejection of the façade’s composition.

The beauty–emotion cluster of ten descriptors captures positive-valence human responses in a direct, visceral way. When architectural forms violate gravitational expectations, people experience confusion and heightened anxiety. ChatGPT effectively picked up these reactions, giving those unbalanced LHS window compositions a low emotional score. Combining Alexander’s 15 properties (that evaluate overall morphological coherence) and the 10 emotional indicators (that capture direct human responses, including gravity-related cues) provides a more holistic assessment of façade quality (Figure 11).

How do we interpret the finding that dominant architectural culture prefers designs that rank as less desirable for human health? This phenomenon is not only confined to an architectural elite of schools, prestigious prizes, and specialized discourse, but it is accepted by the general public. Both government and private clients approve and commission designs that embed precisely those geometrical characteristics that this paper questions. Such geometries are identified as “cutting-edge” and “progressive”.

Contemporary architecture, going back to early Modernism at the beginning of the 20th century, has favored geometries less supportive of psychological health. Addressing this question needs to delve into economic, historical, and ideological factors to deepen the analysis. Such an investigation is beyond the scope of the present paper, however.

Relevant research today, occurring mainly outside architectural academia, is accumulating a knowledge base that bypasses inconclusive and tedious debates on politics and style [50]. Responses to the environment that affect health and well-being can be documented for future use in design by focusing on evolutionary biology and neuroscience.

Animals evolved visual perception to interact effectively with their environment. Inherited neural circuits trigger deep-seated responses set by ancestral mechanisms of visual processing. The discomfort and stress documented through AI experiments with simple window compositions affect human cognitive and emotional health [32]. The modernist movement sought to transcend what were deprecated as being “primitive” sensory reactions because those validated traditional architectural forms. Implementing biologically disruptive designs, however, also rejects the development of an expert knowledge system [50]. Without a reference base, diagonal and misaligned windows—configurations that neuroscience identifies as inducing alarm responses—have become widespread.

Human evolution fused multiple organ systems into a single “gravity-detector” circuit. The vagus nerve (connecting the abdomen to the brain) links gravitational perception to the functioning of the brain, gut, and heart. It acts as a mediator between visual information and physiological states. Moreover: (i) Locomotion is gravity-driven, with the body falling forward and adjusting the placement of our feet to achieve walking motion. (ii) Gravitational pull facilitates the movement of food through the digestive tract. (iii) Elimination processes depend on anatomical structures oriented vertically to remove waste from the body. (iv) The vestibular system in the inner ear provides equilibrium and orientation signals, constantly calibrating the body’s vertical alignment. (v) The vestibular system also monitors motion.

Buildings with gravity-defying or tilted features provoke a disruption of biological homeostasis that affects cardiac control and heart-rate variability; digestive efficiency and gastrointestinal motility; higher-order cognitive functions such as the brain’s executive control and spatial attention mechanisms; adrenal-hypothalamic-pituitary cortisol (stress hormone) release; limbic emotion-regulation circuits; postural stability; and vestibular (balance) equilibrium [89,90,91,92,93]. Cumulative effects of continuous yet subtle stressors, triggered by autonomic alarm systems every time someone looks at an “unbalanced” façade, threaten long-term well-being.

Architects would never express their intentions in terms of “creating ugliness”. Education and professional training have systematically conditioned them to prioritize certain values over biologically informed and human-centered approaches. Specifically, contemporary and modernist architectural theories—rooted in abstraction, conceptual provocations, minimalism, and novelty—strongly reject conventional notions of beauty. As a result, the architectural profession equates esthetic innovation with a break from what it perceives as historical styles.

Many architects have internalized the notion that genuine artistic creativity involves disruption and provocation rather than empathetic resonance and psychological nourishment. Thus, a deeply entrenched ideological commitment rejects objective beauty that aligns with biological and neurological criteria. However, if personal creativity were the dominant factor, we would occasionally witness beautiful windows being produced, at least accidentally. Yet contemporary industrial windows are consistently standardized, uniformly ugly, and appear intentionally designed to minimize emotional and psychological engagement.

Clearly, a major program of future research is necessary to understand what is happening with architecture. If fashionable trends indeed contain unhealthy elements, then those must be identified by scientific means, and the public alerted to the fact. The present experiments with generative AI are only an indication of what is possible, meant to encourage extensive medical trials on how building façades affect people’s health. Academia and the profession have to change their perspective, from a detached concern with abstract form-making, to measuring how shapes and spaces influence the human body.

6. From AI Choice Profiles to Design Grammar for Healthy Windows

It is possible to go one step further and derive a practical design guide for psychologically healthy windows. The method of using generative AI in a feedback loop has achieved resounding success in other fields. ChatGPT read the first part of this paper to come up with a detailed set of window design rules. It adopts the two sets of geometric plus emotional criteria as the basis for a practical toolkit. Additional results are drawn from open-source data and go beyond what was presented above in the qualitative pairwise evaluations. This gives an AI-generated, physiologically validated design code for a façade component.

Prompt to ChatGPT o3: “What is the next step after reading this paper? Based on Christopher Alexander’s 15 fundamental properties and the 10 beauty-emotion qualities in this paper, a set of window designs and compositions have healthier psychological responses than others. Can you extract design rules for the optimal window shape and composition? This would be a broad set of geometric rules for achieving windows that seem empathetic and nourishing when seen from the outside on a building’s façade”.

ChatGPT o3: “Matching the structural mechanisms in the list of 15 fundamental properties with measured psychophysiological thresholds yielded the rules below. The immediate research step is therefore translational: turn the statistical preferences recorded by the AI (and echoed by eye-tracking and EEG work) into explicit geometric rules that an architect, urban designer or generative algorithm can apply.

Ten evidence-based rules for “empathetic” windows:

• Vertical, human-scaled rectangles (height to width ratio ≈ 1.4–2.0) or gentle segmental arches. Avoid triangles or diagonal tops.
• Nested panes and muntins create a 3–5-step scaling hierarchy inside each opening. Keep each level ~½–⅓ the size of the next.
• A thick frame (≈⅕–⅓ of glazing width) and a deep reveal (>75 mm) strengthen the window as a center.
• Keep bilateral symmetry across the vertical axis of each bay, and line lintels and sills horizontally across bays. No random offsets.
• Use rhythmic alternation (ABAB …) along the façade—e.g., narrow–wide–narrow—but keep the pattern legible. No monotone repetition.
• Recess the glazing 50–150 mm so wall and frame interlock (chamfer or molded reveal), casting a graded shadow band.
• Maintain a solid-void ratio around 25–40% on the main street façade. Too little glass feels imprisoning; an all-glass wall erases positive space.
• Add micro-scale texture—beveled muntins, shadow lines, relief carvings—rather than perfectly flush aluminum extrusions.
• Use color or material contrast (e.g., dark frame/light wall) to outline the opening, but avoid high-gloss mirror-like glare.
• Orient sill height so that seated eye-level (≈1.5 m) aligns with the lower third of the glazing when viewed from outside, linking interior gaze to street life”.

The above list is surprisingly detailed. AI took the logical framework developed in the first part of this paper and filled out details and dimensions from open-access literature on window psychology. A considerable amount of empirical research exists, but it is isolated and scattered: the present qualitative model enabled a coherent synthesis. Future AI-based façade evaluations can use these ten design rules in generative models, narrowing the search space to evidence-based solutions linked to well-being. The design rules are guidelines intended to enhance health rather than strict prescriptions that restrict creativity.

The ten schematic window pairs (Figure 1, Figure 2, Figure 3, Figure 4, Figure 5, Figure 6, Figure 7, Figure 8, Figure 9 and Figure 10) were intentionally rendered as austere line diagrams because the experiment’s first task was to isolate “first-order” geometric primitives—alignment, aspect ratio, hierarchy, symmetry—free from confounding influences such as color, dimensions, material texture, or urban context. This reductionist strategy parallels classical psychophysics, where researchers strip a stimulus to its simplest expression in order to probe one visual channel at a time. Adding more complexity would blur causal links and mask the mechanisms to be discovered. By evaluating these stripped-down geometries in pairwise comparisons, ChatGPT replicates well-documented human preference patterns and thereby validated the underlying model. Only after that validation could the elementary findings be safely elaborated into the ten evidence-based rules listed above. Thus, the paper follows a deliberate progression, from abstract and general, through model confirmation, to detailed, actionable design code for empathetic windows.

Nevertheless, the author anticipates a possible point of criticism from the profession that must be answered and deflected beforehand. These recommendations are not stylistically conservative preferences. A similar list of rules for window design and composition could be put together by architects practicing today in a classical or traditional idiom. Because of this similarity, the above design rules might be misinterpreted and dismissed out of hand. ChatGPT was asked for more details of its derivation, with its slightly edited answer given below.

Prompt to ChatGPT o3: “Your list of “Ten geometric rules for empathetic windows” reads like a design guide to traditional windows. Answer this very important question: did you derive these rules entirely from neuroscientific and psychophysiological responses to window geometry, or did you extract them visually from the large number of images of traditional windows on the web?”

ChatGPT o3: “The ten rules come from biology, not from “copy-pasting” traditional façades. The start point is the AI façade-preference experiment in this paper + Alexander’s qualitative mechanisms. For every mechanism that looked important (boundary thickness, symmetry, etc.) I searched open-access neuroarchitecture/environmental-psychology papers that report quantitative turning-points (EEG, GSR, HRV, eye-tracking, SAM, POE surveys). No visual scraping or frequency counts of “traditional window” photos were used. The outcome “looks traditional” because millennia of empirical building practice converged—often unintentionally—on geometries that human biology finds legible, calming and socially intelligible. The rules re-discover those patterns through 21st-century neuroscience rather than deriving them from a photo-archive. The pipeline was theory → biometric data → design rule. Traditional precedents merely happen to satisfy the rules; they were not the data source”.

This detailed and logical explanation should clear up any ambiguity and potential misreading. ChatGPT not only justified its derivation scientifically; it also gave a valuable summary of why empathetic design naturally converges on traditional window typologies. The list of 10 design rules represents a scientific finding accelerated by AI, using digital architecture as an emergent information processing system. A further study could apply the above ten criteria to derive a visual classification of window types, but that task lies beyond the scope of the present paper.

AI turns the apparently subjective realm of architectural design into a scientifically tractable domain. Although architecture is a human artifact, successful buildings embed biomechanical and social constraints, evolved regularities, and perceptual affordances. AI can identify and model these repeatable, tested patterns while ignoring random design variations. But styles that decouple from embodied fitness signals—e.g., blank glass curtain walls, and tilted forms that defy intuitive gravity cues—discard the regularities that make prediction feasible.

7. Industry Lock-In of Stress-Producing Façades

AI can do even better in a second iteration of this paper. The first iteration used the emotional plus geometrical criteria formulated in Section 1, Section 2, Section 3, Section 4 and Section 5 to derive the 10 rules for empathetic window design (Section 6). A second iteration should hopefully give some new insight, since the inherent power of generative AI is to derive progressively better results arising out of a feedback loop. A second-iteration result uses ChatGPT to read this paper again (this time with Section 6 included), asking the model to select inadequate window typologies.

The simplest quantification of a diagnostic model based upon the 10 empathetic window rules in Section 6 counts 0 or 1 for the absence or presence of each feature, then adds those numbers up. ChatGPT calls this set of estimates the “rule-compliance vector”. This evaluation compresses the results from the ten rules into one number. Out of many possible topics for investigation, it was decided to focus here on the lowest ranking window typologies because this result is likely the most controversial. Two answers from ChatGPT are reproduced below with minimal editing.

Applying the ten empathetic window rules synthesized in Section 6 to every known contemporary window archetype, ChatGPT ranks them by cumulative rule-violations and discovers the seven worst scorers. Those happen to be the window systems that today’s industry implements most widely. A century-long convergence of economic, ideological, and regulatory forces has narrowed design decisions down to those seven typologies.

Prompt to ChatGPT o3: “Can you compute the rule-compliance vector for the standard industrial window typologies in use today? I want only the lowest ranking ones, namely those that are identified as having high stress potential”.

ChatGPT o3: “Below are four standard industrial window typologies that emerge at the bottom of the empathetic-window grammar and well-being scale:

• Unitized flush curtain-wall panel (floor-to-ceiling glass, aluminum caps hidden).
• Horizontal ribbon window (continuous strip, 1.1 m high).
• Frameless triangular aperture set into rainscreen.
• Tilted diagonal picture window (rectangular sash rotated 35°)”.

Standard industrial window typologies in wide use today did not come out well in the present analysis. Even so, many other unusual window arrangements and designs are seen around the world on contemporary buildings. Those look very different: they tend to be associated with iconic designs and are not part of established industrial production. They are custom-made for each case, hence much more expensive to build. A second inquiry is necessary to cover those separate geometrical categories.

Prompt to ChatGPT o3: “Your previous answer was to identify standard industrial window typologies that score low on the empathetic scale. Those are mass-produced globally. Yet we also see an increasing use of custom-made façades and windows that embody randomness, either in window positioning, or in window subdivision. Identify those typologies that have high-stress potential in this model”.

ChatGPT o3: “The ten-rule framework can be applied to the new generation of one-off, parametric façades whose selling point is deliberate randomness. When the whole wall is assessed—rather than any single opening—these compositions breach the pattern-forming cues that calm the visual system, driving the empathetic-window grammar and well-being scale into the high-stress band.

A.

Tilt & shuffle rotated quadrilateral windows. Each unit is a parallelogram rotated 20–40°, positions jittered floor-to-floor.

B.

Barcode ribbon with random mullion spacing. A continuous strip of glass spans the façade, but vertical mullions of unequal width are inserted at irregular x-positions.

C.

Diagonal scatter punched windows. Identical rectangular windows but placed on a diagonal grid or eccentric centers, ignoring the building’s structural bay”.

In practice, the model therefore tags these bespoke, “signature” façades as equal-or-worse for stress than the mass-produced curtain wall they were meant to replace”.

Many architects today implement any one of the seven window typologies identified above. Practitioners who may feel uncomfortable with the rankings are invited to question or refine these conclusions arising out of AI using emotional plus geometrical criteria. Readers are welcome to use the tools outlined here for performing this type of analysis. What is clear is the need for a new in-depth investigation of the effects of different window typologies on human psychological health. Generative AI suggests a promising direction of research.

A third iteration with ChatGPT determines the individual weights of each of the 10 rules for empathetic windows given in Section 6. They do not contribute equally. It turns out that each of the first four variables (aspect ratio; hierarchical panes; frame thickness and reveal depth; bilateral symmetry and lintel alignment) has more impact than any of the remaining six rules, and together, they explain a major part of the positive-valence effect. Further refinements of this model will not be carried out here, however.

Finally, the generative AI analysis identified seven contemporary window typologies which are currently dominant worldwide—each independently shown to produce heightened anxiety and negative emotional responses in observers. Astonishingly, these typologies have systematically replaced traditional window forms, which historically elicited positive emotional and physiological reactions. Unlike natural ecosystems, where adaptive traits and survival fitness drive evolutionary outcomes, the architectural environment’s selection process derives entirely from human choices made by architects, clients, critics, decision-makers, and public agencies.

Codes enforce energy and structural safety, not neurophysiology, leaving a huge regulatory blind spot. The paradox is that we possess tools for custom designed windows; yet seem constrained to a narrow set of typologies that do not reflect human experience.

8. Conclusions

Ten rough sketches of similar window pairs were analyzed by the large-language model ChatGPT 4.5. Examples on the LHS of each figure deliberately allude to the types of windows and their placement favored by dominant architectural culture. Those were contrasted with windows from more traditional typologies: examples on the RHS of each figure. ChatGPT invariably picked all the traditional compositions as being more desirable. Some readers might find this result disconcerting; however, two independent generative AI experiments reinforced each other. Window appeal is explained by emotional responses, as well as from the human body’s innate preference for living geometry. Human evolution has hard-wired those mechanisms.

AI was subsequently used in a feedback loop, as ChatGPT o3 read the results of the survey in the first part of this paper. On that basis, it was asked to derive detailed and explicit rules for designing “empathetic” windows, and it produced a list of ten design rules. Anticipating a possible misunderstanding, further questioning clarified that those rules come from psychophysiological data and not by copying window designs from Classical or traditional buildings. AI then applied its own derived criteria to list the seven least desirable window typologies according to the anxiety they generate in a viewer.

The present pilot study provides concrete recommendations for architects, policymakers, and urban planners on how to implement these findings. It is a simple matter to revise standard window designs that are mass-produced globally. Once the market begins to demand the new (actually, traditional) archetypes, then industry will follow suit. But the public will not shift its taste until it understands the health benefits from doing so. For this reason, future research is needed using human-subject experiments in real-world scenarios, especially longitudinal studies of health outcomes in complex urban contexts.

In conclusion, the industry has standardized windows to systematically exclude known sources of biological resonance and emotional nourishment. A critical but overlooked factor is societal habituation. After decades of exposure to monotonous, uncompromising façades and window designs, public perception of what constitutes a healthy building esthetic has shifted. Society has become resigned to these emotionally deadening and sometimes unsettling designs. People may subconsciously avoid acknowledging the extent of stylistic dominance to avoid cognitive dissonance and feeling helpless. Thus, there is minimal pressure from the market to change existing practices.