Design Exploration of AI-assisted Personal Affective Physicalization

2025-09-25

AI Summary

This study addresses the challenge of concretizing abstract emotions in design. We propose an AI-augmented framework for emotional physicalization, developed through Research-through-Design. Central to this framework is *PhEmotion*, a tool that leverages large language models (LLMs) to extract multidimensional affective features from human–AI dialogues and drive parametric modeling to generate personalized physical artifacts. A user study with 14 participants demonstrates that AI fundamentally reshapes designers’ strategic choices and meaning-making processes—enhancing reflective depth and expressive diversity while introducing critical tensions around human–AI intention alignment and agency distribution. This work provides the first systematic account of affect-to-form mapping mechanisms and challenges under AI collaboration. It establishes *emotional physicalization* as a novel research direction within affective design and contributes foundational theoretical insights and practical methods for explainable affective AI and embodied interaction design.

Technology Category

• Humans and AI: Emotional Intelligence
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Intelligent Robots: Embodied AI

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Personal Affective Physicalization is the process by which individuals express emotions through tangible forms to record, reflect on, and communicate. Yet such physical data representations can be challenging to design due to the abstract nature of emotions. Given the shown potential of AI in detecting emotion and assisting design, we explore opportunities in AI-assisted design of personal affective physicalization using a Research-through-Design method. We developed PhEmotion, a tool for embedding LLM-extracted emotion values from human-AI conversations into parametric design of physical artifacts. A lab study was conducted with 14 participants creating these artifacts based on their personal emotions, with and without AI support. We observed nuances and variations in participants' creative strategies, meaning-making processes and their perceptions of AI support in this context. We found key tensions in AI-human co-creation that provide a nuanced agenda for future research in AI-assisted personal affective physicalization.

Problem

• Exploring AI-assisted design for emotional physicalization challenges
• Developing tools to embed emotion values into physical artifacts
• Investigating human-AI co-creation tensions in affective representation

Innovation

• AI-assisted design for affective physicalization creation
• LLM-extracted emotion values embedded in artifacts
• Parametric design tool for personal emotion representation