When designing Affective Health, a mobile stress management tool using biosensors, we gradually understood how severely limited inferences can be when we move from laboratory situations to everyday usage. We also came to understand the strong connection between our subjectively perceived resources for dealing with stress and healing. Therefore, rather than employing a diagnose-and-treat design model, we propose that designers empower users to make their own reflections and interpretations of their own bio-sensor data. We show how this can be done through encouraging reflection, alternative interpretations and active appropriation of biosensor data – avoiding a reductionist, sometime erroneous, mediation of automatic interpretation from bodily data to emotion models or, in this case, stress diagnosis.