In our current work we have designed and implemented an artificial pet with two embodiments. In both embodiments behavior is driven by needs that are used to maintain coherence and motivate user interaction. These needs are transferred between embodiments, with only one embodiment being active at a time. We performed an evaluation with 10- year old children participants. The retrieved data indicated that many children understood the concept of an artificial pet with two bodies, even without being given clues. Nevertheless, children did perceive differences between the two embodiments, which contributed for many stating that they interacted with two pets. Among other aspects, the physical version was perceived as less obedient due to problems concerning action recognition. Although caused by technical issues, this result raises the question if virtual embodiments should simulate action recognition problems that their physical counterparts have.