Robot companions often default to cisnormative and heteronormative assumptions, undermining trust and inclusion for LGBTQIA+ (queer) communities. Although inclusivity is widely discussed in HRI, empirical, community-led insights into queer needs and risks remain limited. We address this gap through a mixed-methods study of how queer individuals envision affirming and trustworthy robot companions, combining an online survey of community priorities with participatory design workshops exploring lived experiences and design tensions. Although many participants felt they were not the "intended user" of current technologies, they outlined clear priorities for future robot companions, including accurate handling of names and pronouns, robust privacy and data safeguards, clear and bounded utilitarian roles, and user-controlled adaptability, while identifying risks such as misgendering, surveillance, stereotype reinforcement, and unhealthy dependence. We translate these findings into justice-oriented design requirements for robot companions serving queer and other marginalized communities.