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).

He had been enjoying himself, or at least pretending to. Then he saw her. Across the crowded hall, amidst the flashing lights and joyful chatter, she stood, radiant. It was like a physical blow. The air rushed from his lungs.

The carefully constructed wall he had built around his emotions began to crumble. His smile faltered, replaced by a strained expression. He found himself focusing on the pattern of the tablecloth, suddenly and intensely interested in the woven threads.

He felt a deep and pervasive sense of isolation. The noise of the party receded, replaced by the deafening silence of his own thoughts. He just wanted it to be over.

Emotion: hurt

Cluster: Fear / Anxiety
PC1 (Valence): -2.46 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.412
L0.396
ness0.338
😞0.328
😢0.290
Suppressed:
de-0.643
la-0.402
!-0.259
(!)-0.248
/-0.244