This study explores the design of conversational companion robots for older adults, focusing on their social and emotional support needs. The authors conducted participatory design workshops with 28 Swedish-speaking older adults to understand their expectations and preferences for such robots. Key findings include the importance of active listening, passive listening in social settings, personalization, privacy protection, information retrieval, social connectedness, and emotional expressiveness. The study recommends integrating foundation models, such as large language models (LLMs), into the design to enhance these capabilities. Specifically, the recommendations emphasize the need for dynamic listening strategies, lifelong learning, and personalized interactions to meet the diverse needs of older adults. The study also highlights the importance of user feedback and co-design processes to ensure that the robots align with the values and expectations of older adults.This study explores the design of conversational companion robots for older adults, focusing on their social and emotional support needs. The authors conducted participatory design workshops with 28 Swedish-speaking older adults to understand their expectations and preferences for such robots. Key findings include the importance of active listening, passive listening in social settings, personalization, privacy protection, information retrieval, social connectedness, and emotional expressiveness. The study recommends integrating foundation models, such as large language models (LLMs), into the design to enhance these capabilities. Specifically, the recommendations emphasize the need for dynamic listening strategies, lifelong learning, and personalized interactions to meet the diverse needs of older adults. The study also highlights the importance of user feedback and co-design processes to ensure that the robots align with the values and expectations of older adults.