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).

The fluorescent lights in the pawn shop seemed to intensify the shadows clinging to Mark. He felt emotionally exposed, every detail a reminder of his loss. He spotted it in a display case. His grandmother's ring. He stumbled toward it, his legs suddenly weak.

He felt a choking sensation in his throat, a painful constriction that made it difficult to breathe. He remembered the feel of her hand in his. A tear escaped, trailing down his cheek. He wiped it away, hoping it would not be noticed.

The shop owner, a man with a thin mustache, asked what he wanted. He pointed towards the ring, unable to speak. The ring was a symbol of love, of permanence. Now it was here.

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