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).

John walked through the deserted halls of the art building, the echoing silence amplifying his grief. The scent of paint and turpentine, once a source of inspiration, now felt melancholic. The canvases stacked against the walls seemed to mock him, unfinished projects that would never be.

He ran a hand across a half-finished sculpture, its rough texture a painful reminder of his thwarted ambitions. He sank into a chair, the weight of his unfulfilled dreams pressing down on him.

He was a ghost in his own future, all possibility, all hope, dissolving into the ether. The world felt devoid of color, of promise.

Emotion: sorry

Cluster: Sadness / Despair
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.36

Role in Research

This story is one of 1,000 stories generated for the emotion sorry. 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 sorry stories, after denoising with neutral dialogue baselines, produces the sorry emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
S0.604
L0.549
😞0.382
😔0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288