Students' effort and emotions are important contributors to math learning. In a recent study evaluating the efficacy of MathSpring, a scalable web-based intelligent tutoring system that provides students with personalized math problems and affective support, system usage data were collected for 804 U.S. 10-12-year-olds. To understand the patterns in students' interactions with MathSpring and how patterns vary across students, hierarchical cluster heatmap analysis was performed. Guided by the patterns from the heatmap, latent profile analysis was conducted to identify student subgroups. Both analyses indicated that there were two groups of students: "Confident Solvers" who solved problems on their first attempt and reported high confidence, and "Struggling Solvers" who gave up, did not read problems, and reported higher frustration. These analyses provide insight into students' behaviors in online learning environments that can be scaled to students nationwide. Developers can use these insights to design systems that respond to students' usage and inform teachers about students' effort and emotions. [This paper was published in: "Proceedings of the Twelfth ACM Conference on Learning @ Scale (L@S '25), July 21-23, 2025, Palermo, Italy," ACM, 2025.]