Imagine the brain as a vast city at night. Thousands of lights turn on and off simultaneously in every district. At first glance, it seems like a chaotic flicker. But if you observe for a long time, you can notice patterns: when a person is happy, the 'light pattern' is one, when they are anxious, it's completely different.
This is precisely what a new study, published in Nature Computational Science, is dedicated to.
Scientists worked with 18 epilepsy patients who, for medical reasons, already had electrodes implanted in their brains. While participants looked at emotional images and video clips, they continuously rated their feelings: how pleasant or unpleasant the emotion was and how intense it was. Simultaneously, a computer recorded their brain's electrical activity.
Then, the researchers trained an artificial intelligence to find connections between these signals and what the person was feeling. As a result, the system learned to identify emotional states with considerable accuracy in near real-time.
The most interesting part turned out to be something else. Previously, most similar studies analyzed only the activity of the brain's gray matter – where the neuron cell bodies are located. But the authors decided to also include signals from the white matter – the 'cables' that connect different brain regions.
It turned out that it is through these neural highways that a huge amount of information about emotions travels. When the model considered both gray and white matter simultaneously, its accuracy noticeably increased.
Just a few years ago, it was believed that emotions are born mainly in specific structures, such as the amygdala. The new work reveals a more complex picture: a feeling does not reside in a single brain area. It arises from the coordinated work of an entire network, uniting the cortex, thalamus, limbic system, and the neural pathways connecting them.
But an interesting philosophical question arises.
If a computer can determine that a person is anxious or happy, does that mean it has 'read' their feelings?
Not entirely.
The algorithm recognizes patterns of electrical activity that typically accompany certain experiences. It's like a weather forecast. Based on clouds, humidity, and pressure, you can predict rain with almost no error, but the instruments themselves don't feel the smell of wet earth or the coolness of the first drops.
It's the same here. Artificial intelligence has learned to predict emotions, but this doesn't mean it knows what joy, fear, or love is like from the inside.
This is a very important result for modern neuroscience. It aligns well with predictive processing theories, which suggest that the brain constantly builds predictions about what is happening inside the body and in the external world. Emotions, in this view, do not arise as distinct 'happiness buttons' or 'fear centers,' but as a result of continuous comparison between the brain's expectations and what is actually happening.
The study also has limitations. All participants were epilepsy patients, so the results cannot be automatically generalized to the entire population. Furthermore, the participants themselves rated their emotions, and the real-time mode has so far only been tested on four individuals.
Nevertheless, the work demonstrates how rapidly the field of neurotechnology is advancing. In the future, such systems could help detect the onset of depression, anxiety attacks, or emotional breakdowns even before a person becomes aware of what is happening. This opens up new possibilities for treating mental disorders.
But at the same time, a new ethical question arises: if technology eventually learns to recognize our emotions very accurately based on brain activity, where should the line be drawn between medical assistance and a person's right to privacy of their inner world? This question, perhaps, will become one of the main challenges for neuroscience in the coming years.
