Purpose: This paper aims to understand what drives people -- their motivations, autonomous learning attitudes and learning interests -- to volunteer as mentors for a program that helps families to ideate technological solutions to community problems. Design/methodology/approach: A three-phase method was used to build volunteer mentor profiles; elicit topics of interest and establish relationships between those. The mentor profiles were based on self-assessments of motivation, attitude toward lifelong learning and self-regulated learning strategies. The topics of interest were elicited through content analysis of answers to reflection questions. Statistical methods were applied to analyze the relationship between the interests and the mentor profiles. Findings: Bottom-up clustering led to the identification of three mentor groups (G1 "low"; G2 "high" and G3 "medium") based on pre-survey data. While content analysis led to identifying topics of interest: communication skills; learning AI; mentoring; prototype development; problem-solving skills; working with families. Analyzing relationships between mentor profile and the topics of interest, the group G3 "medium," with strong intrinsic motivation, showed significantly more interest in working with families. The group with the overall highest scores (G2 "high") evidenced also substantial interest in learning about AI, but with high variability between members of the group. Originality/value: The study established different types of learning interests of volunteer mentors and related them to the mentor profiles based on motivation, self-regulated learning strategies and attitudes toward lifelong learning. Such knowledge can help organizations shape the volunteering experience to provide more value to volunteers. Furthermore, the reflection questions can be used by volunteers as an instrument for reflection and by organizations to elicit the learning interests of volunteers.