Embodied intelligent virtual agents are expected to operate as persistent, adaptive, and context-aware entities within complex virtual and Metaverse worlds. However, implementing cognitively capable agents in such environments is conceptually and technologically challenging. This paper explores the use of Small Language Models (SLMs) to support edge-based operation of selected CEAA components, focusing on "Think" and "Memory" as processes central to cognitive orchestration and persistence of virtual agents. An edge-based virtual agent gateway system was developed and evaluated on an NVIDIA Jetson Orin NX using Qwen2.5 models of different sizes. The results demonstrate an SLM-driven prototype agent system that partially implements selected CEAA processes to support the development of embodied agents whose cognitive "brain" can operate efficiently and contextually for interactive experiences in immersive virtual worlds. Blogger's Review: This paper provides a new solution for virtual agents' cognitive abilities, and the combination of SLMs and edge computing provides new possibilities for the development of virtual worlds and the Metaverse.