In order to give assertive support, robots need to understand the cognitive and emotional characteristics of learners while in the learning process. Also, if the task involves handling capacity, robots must have similar skills. Three concepts were explored to control the cognitive and emotional robot’s behavior: the psychological flow theory, the scaffolding pedagogic strategy, and the multiagents-software paradigm. Based on these concepts, the Human-Robot Scaffolding architecture was designed. It is divided into five blocks. First, the sensory block recognizes body gestures, speech, and task state. Second, the beliefs block estimates the skills and emotional state of learners. Third, the desires block validates the goals the robot can reach; the goals are grouped in skills development, emotional control, cognitive control, challenge control, life signals, and immediate support. Fourth, the intentions block, based on the goals competition strategy, selects the goal that the robot will perform. Finally, the action-planner block regulates the robot’s movements according to the robot’s emotions. The validation procedure was done with 53 learners ranging between 10 and 13 years old who study in public and private schools. Based on the research achievements, the robot fosters learning the Mean-Ends Analysis strategy and the solution of a problem. A video fragment that summarizes the research process is available in https://youtu.be/qbohCjBIwYc.