In this study, we investigate if a digital coach for low-literate learners that provides cognitive learning support based on scaffolding can be improved by adding affective learning support based on motivational interviewing, and social learning support based on small talk. Several knowledge gaps are identified: motivational interviewing and small talk must be translated to control rules for this coach, a formal model of participant emotional states is needed to allow the coach to parse the learner's emotional state, and various sensors must be used to let the coach detect and act on this state. We use the situated Cognitive Engineering (sCE) method to update an existing foundation of knowledge with emotional models, motivational interviewing, and small talk theory, technology, and a new exercise in the volunteer work domain. We use this foundation to create a design specification for an Embodied Conversational Agent (ECA) coach that provides cognitive, affective, and social learning support for this exercise. A prototype is created, and compared to a prototype that only provides cognitive support in a within-and between-subjects experiment. Results show that both prototypes work as expected: learners interact with the coach and complete all exercises. Almost no significant differences are found between the two prototypes, indicating that the affective and social support were not effective as designed. Potential improvements are provided for future work. Results also show significant differences between two subgroups of low-literate participants, and between men and women, reinforcing the importance of using individualized support measures with this demographic.