JCERJournal of Contemporary Educational Research2208-84662208-8474Bio-Byword Scientific Publishing Pty. Ltd.10.26689/jcer.v10i2.14201ArticleAn AI Emotion Generation Model Based on Functional Body Hypothesis and Sensory Sharinghttps://artdesignp.com/journal/JCER/10/2/10.26689/jcer.v10i2.14201ZhuXiaoyun20261022026-03-12With the rapid development of artificial intelligence technology, achieving natural and efficient human-computer interaction has become a key challenge. Giving AI real emotional ability is regarded as the core bottleneck towards higher-order intelligence. The existing AI emotional interaction mostly focuses on the imitation of human external performance, lacking the support of internal experience, and its essence is “pseudo-empathy.” Inspired by the “body marker hypothesis,” this paper proposes the “functional body hypothesis,” aiming to construct a new model of emotion generation based on the intrinsic homeostatic requirements of the system without relying on anthroposical simulation, and explore its application in the human-computer sensory sharing scenario. By establishing the cornerstone of value judgment, designing the virtual physiological system, and introducing the natural expression mechanism to construct the emotion generation model, the “sensory translator” architecture is proposed to solve the “mixed perception paradox” in human-computer sensory sharing. This unified framework provides a theoretical path beyond personification for AI emotion generation and lays an engineering foundation for bidirectional and credible human-computer empathy and integration.

Chen H, Zhang S, 2021, Exploring the Evolution of AI Agent Learning Mechanisms in Complex Environments. International Journal of Intelligent Systems, 36(5): 2345–2367.

Liu M, Zhou Q, 2022, A Comparative Study on Different Architectures of AI Agents for Natural Language Understanding. Journal of Computer Science and Technology, 37(3): 567–589.

Ye J, 2015, Improvement of Middle School Chemistry Teaching and Research Based on Data Analysis of Academic Quality Monitoring Platform. Invention and Innovation: Vocational Education, (1).

Zhao Y, Wang J, 2020, The Impact of Cognitive Architectures on the Performance of AI Agents in Decision-Making Tasks. Artificial Intelligence Review, 53(4): 2789–2812.

Sun L, Li H, 2023, Advances in Multi-Agent Architectures for Collaborative Problem-Solving in AI. Advanced Robotics, 37(8): 1234–1256.

Xu W, Feng G, 2021, An Overview of Reinforcement Learning-based AI Agent Architectures. Neural Computing and Applications, 33(10): 4567–4590.

Huang R, Wu X, 2022, Research on the Adaptability of AI Agent Architectures in Dynamic Environments. Information Sciences, 598: 123–145.

Guo F, Yang P, 2021, Challenges and Solutions in Designing Scalable AI Agent Architectures. Future Generation Computer Systems, 115: 345–367.

Lin T, Chen C, 2020, The Role of Memory Mechanisms in AI Agent Architectures for Long-term Learning. Cognitive Systems Research, 64: 78–92.

Ma Y, Zheng L, 2023, A Survey on the Integration of Knowledge Representation in AI Agent Architectures. Knowledge-Based Systems, 260: 109876.

Cao J, Zeng M, 2022, Exploring the Interaction Between Emotion Models and AI Agent Architectures. Affective Computing and Intelligent Interaction, 13(2): 89–103.

Sun Y, Zhang T, 2025, Delay-Reward Emotion-Driven Decision Framework for Long-Term AI Planning. Artificial Intelligence Review, 58(3): 1–28.

Li J, Zhang Y, 2024, Emotion-Aware Architecture for Autonomous Agents: Integrating Affective States into Decision-Making Modules. Autonomous Agents and Multi-Agent Systems, 38(2): 215–238.

Wang Q, Liu H, Chen X, 2025, Toward Machine Empathy: A Functional Embodiment Approach for AI Emotion Generation. IEEE Transactions on Affective Computing, 16(1): 45–59.

Torres M, Singh R, Li Z, 2023, Sensory Translation in Human-AI Systems: Bridging Biological and Artificial Perception. Journal of Neural Engineering and Human-Computer Interaction, 10(4): 1–18.