Scientists can’t yet read your mind, but they might be able to identify when you’re in emotional pain. In a new study published in PLOS Biology, psychology researchers from the University of Colorado, Boulder and the University of Pittsburgh report being able to identify the intensity of a negative emotional reaction via the patterns of brain activity with 93 percent accuracy.

More than 180 participants of various ages looked at images designed to elicit negative emotional reactions in the lab (images of injuries, car wrecks, piles of poop, etc.). Another 30 participants received pain stimulation from heat in order to differentiate the brain’s response to physical and emotional pain. The researchers then used a portion of the fMRI scans of these subjects’ brains to create an algorithm that could predict the intensity of the participants’ pain by identifying a distinct pattern of neuron activation.

In tests, this algorithm was able to predict the intensity of the participants’ emotions with a 93 percent accuracy compared to a self-reported survey of their emotional state (a simple numbered scale where 1 indicated neutral feelings and 5 indicated strong negative feelings). The algorithm could also distinguish between physical and emotional pain with 92 percent accuracy.

While less than 200 people is not quite enough to create a definitive neurological illustration of emotional pain, it can provide important data about how the brain processes emotions. “Emotions are central to our daily lives and emotional dysregulation is at the heart of many brain- and body-related disorders, but we don't have a clear understanding of how emotions are processed in the brain,” says lead author Luke Chang, previously a post-doctoral researcher at the University of Colorado and now an assistant professor at Dartmouth. “Thus, understanding the neurobiological mechanisms that generate and reduce negative emotional experiences is paramount.”