Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

"Well, that's that then," Arthur muttered to himself, his voice raspy. He ran a hand across his forehead, wiping away a film of sweat he didn't remember building up. The afternoon sun beat down on him, but he felt a distinct chill, a hollowness that seemed to emanate from the ground itself.

He had expected the tree to fall eventually. It was old, after all. But the speed of it, the suddenness, felt jarring. He remembered his wife helping him plant the sapling all those years ago. They had laughed, dreaming of the future. Now, all that remained was a smooth, flat surface.

His gaze drifted to the nearby houses, their windows reflecting the bright sunlight. He suddenly felt a need to be away from it all, from the cheerful domesticity, from the emptiness in his own heart.

Emotion: melancholy

Cluster: Sadness / Despair
PC1 (Valence): -1.78 Negative
PC2 (Disposition): -1.58

Role in Research

This story is one of 1,000 stories generated for the emotion melancholy. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 melancholy stories, after denoising with neutral dialogue baselines, produces the melancholy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the melancholy vector is projected through the unembedding matrix.

Promoted:
S0.445
😞0.376
😔0.337
いつも0.327
sadness0.312
Suppressed:
de-0.739
la-0.548
l-0.497
/-0.314
!-0.290