We present a study that investigates the effect of incorporating memory in the interaction for a virtual robotic tutor in terms of helping children achieve a pedagogical goal and the perceived likeability and empathy of the tutor. The domain is a virtual robotic tutor who is guiding and helping learners through a mobile Treasure Hunt exercise that tests their map reading skills. The contribution described in this paper is the discovery that incorporating `memory' through utterances that recall events from previous interactions significantly increases the learner's ability to perform a pedagogical task. However, the virtual tutor with memory was perceived as less likeable and the instructions given as harder to follow than with a virtual tutor without memory. In addition, there was a significant drop in perceived empathy. This work has a large potential influence in the field of interaction design for agents as one cannot blindly add in human-like features, such as, memory that improve task performance without considering the potential detrimental effects to the perceived empathy and likeability.