Methods, systems, and devices are disclosed for implementing a low-cost wearable multi-modal bio-sensing system capable of recording bio-markers and eye-gaze overlaid on world view in real-world settings. In an exemplary embodiment, a bio-sensing system uses at least two cameras and one or more bio-sensors to record a variety of events and bio-marker data. In another exemplary embodiment, the recorded information is used to track the eye position, calculate the pupil dimensions, and calculate the gaze of a human being. The eye position and dimensions of the pupil can be used for emotion recognition.