Exploring Human-AI Differences in Emotional Color Perception: A Pictorial Study on GAI-Generated Cinematic Visuals through Design Research

Authors

Hsin-Ting Chung, Department of Design, National Taiwan University of Science and Technology, Taipei, Taiwan
Tingyi Lin, Department of Design, National Taiwan University of Science and Technology, Taipei, Taiwan
Yu-Ting Cheng, Department of Design, National Taiwan University of Science and Technology, Taipei, Taiwan

Abstract

This study explores how generative AI (GAI) and humans interpret emotional meanings through color in cinematic visuals. Drawing from film color theory, we designed a set of mood palettes and applied them to keyframes generated by GAI. Using qualitative questionnaires, we compared emotional interpretations from human participants and GPT-4o. Results revealed overlapping but diverging perceptions: humans relied on narrative context and memory, while AI leaned on statistical associations. These findings highlight GAI’s limited emotional grounding and suggest opportunities to enhance visual storytelling tools through hybrid color-emotion frameworks. This research contributes to emerging dialogues in computational aesthetics, human–AI perception, and design methodology.

Keywords

Emotional Color Palette; Generative AI; Visual Perception; Design Experimentation

DOI

https://doi.org/10.21606/iasdr.2025.1133

Citation

Chung, H., Lin, T.,and Cheng, Y.(2025) Exploring Human-AI Differences in Emotional Color Perception: A Pictorial Study on GAI-Generated Cinematic Visuals through Design Research, in Chang, C.-Y., and Hsu, Y. (eds.), IASDR 2025: Design Next, 02-05 December, Taiwan. https://doi.org/10.21606/iasdr.2025.1133

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License

Conference Track

Track 3 - Design, Art & Technology