Expressive agents in psychology research: a study on nuanced emotional signaling with dynamic tears

Virtual agents (VAs) are increasingly used in psychology, healthcare, and education, yet realistic representations of nuanced emotional signals like tears remain underexplored. We present a novel real-time system that simulates dynamic, physics-based tears in high-fidelity Metahuman avatars using Unreal Engine 5.5. Unlike traditional shader or animation tricks, our system produces lifelike crying effects through Niagara's skeletal mesh traversal, custom scratch modules, and real-time surface interaction. In a first empirical study (N=56), we compared static and dynamic crying avatars. Results showed that dynamic tears significantly enhanced perceived sadness and emotional contagion, without altering perceived authenticity. These findings suggest that flowing tears amplify social sadness signaling. Our demo will showcase the system's technical design, research methodology, and results. This work contributes to the development of emotionally expressive VAs. It bridges insights from psychology and computer graphics to advancing the study of nuanced human-agent emotional communication.