Biomimetic Synthetic Somatic Markers in the Pixelverse: A Bio-Inspired Framework for Intuitive Artificial Intelligence.

Biological decision-making under uncertainty relies on somatic markers, which are affective signals that bias choices without exhaustive computation. This study biomimetically translates the Somatic Marker Hypothesis (SMH) into synthetic somatic markers (SSMs), a minimal and interpretable evaluative mechanism that assigns a scalar valence to compressed environmental states in the high-dimensional discrete grid-world Pixelverse, without modelling subjective feelings. SSMs are implemented as a lightweight Python routine in which agents accumulate valence from experience and use a simple threshold rule (θ = -0.5) to decide whether to keep the current trajectory or reset the environment. In repeated simulations, agents perform few resets on average and spend a higher proportion of time in stable "good" configurations, indicating that non-trivial adaptive behaviour can emerge from a single evaluative dimension rather than explicit planning in this small stochastic grid-world. The main conclusion is that, in this minimalist 3 × 3 Pixelverse testbed, SMH-inspired SSMs provide an economical and transparent heuristic that can bias decision-making despite combinatorial state growth. Within this toy setting, they offer a conceptually grounded alternative and potential complement to more complex affective and optimisation model. However, their applicability to richer environments remains an open question for future research. The ethical implications of deploying such bio-inspired evaluative systems, including transparency, bias mitigation, and human oversight, are briefly outlined.