Current quantitative methods of measuring player experience in games are mostly intrusive to play and less suited to natural, non-laboratory play environments. This paper presents an initial study to validate the feasibility of using facial expressions analysis for evaluating player experiences. It builds on a prior position that video-based computer vision techniques can provide a less intrusive and more versatile solution for automatic evaluation of game user experiences. A user study was performed on an initial group of participants in a first-person puzzle shooter game (Portal 2) and a social drawing trivia game (Draw My Thing), and the results are shown to support our position.