Mikasa: A Character-Driven Emotional AI Companion Inspired by Japanese Oshi Culture
Miki Ueno
TL;DR
This work tackles the problem of sustaining long-term engagement with AI companions by arguing that deficits lie more in character design and user AI relationship definitions than in raw model capability. It introduces Mikasa, an emotional companion inspired by Japanese Oshi culture, featuring a stable persona and explicit partner framing, implemented as a client-server architecture on mobile with memory and privacy-preserving speech input. The architecture emphasizes memory management, retrieval-based context for relational coherence, and a Live2D visual embodiment, while design choices position character coherence and relationship framing as infrastructural constraints rather than decorative aspects. An exploratory qualitative evaluation with a small sample suggests that users value the ability to define relationships and the perceived naturalness of dialogue, supporting the claim that structural character design shapes interaction quality and sustained engagement, with broad implications for emotionally grounded companion systems.
Abstract
Recent progress in large language models and multimodal interaction has made it possible to develop AI companions that can have fluent and emotionally expressive conversations. However, many of these systems have problems keeping users satisfied and engaged over long periods. This paper argues that these problems do not come mainly from weak models, but from poor character design and unclear definitions of the user-AI relationship. I present Mikasa, an emotional AI companion inspired by Japanese Oshi culture-specifically its emphasis on long-term, non-exclusive commitment to a stable character-as a case study of character-driven companion design. Mikasa does not work as a general-purpose assistant or a chatbot that changes roles. Instead, Mikasa is designed as a coherent character with a stable personality and a clearly defined relationship as a partner. This relationship does not force exclusivity or obligation. Rather, it works as a reference point that stabilizes interaction norms and reduces the work users must do to keep redefining the relationship. Through an exploratory evaluation, I see that users describe their preferences using surface-level qualities such as conversational naturalness, but they also value relationship control and imaginative engagement in ways they do not state directly. These results suggest that character coherence and relationship definition work as latent structural elements that shape how good the interaction feels, without users recognizing them as main features. The contribution of this work is to show that character design is a functional part of AI companion systems, not just decoration. Mikasa is one example based on a specific cultural context, but the design principles-commitment to a consistent personality and clear relationship definition-can be used for many emotionally grounded AI companions.