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).

"I don't know what I expected," muttered Leo, his voice tight. He knew he was being irrational, but the sight of Chester, his childhood teddy, sitting amongst a pile of broken toys, still filled him with something akin to despair.

He felt the familiar sting in his eyes. He crossed his arms, the action a deliberate attempt to shield himself. He wanted to turn and leave, to pretend he hadn't seen him. But his feet refused to move.

He pushed past the feeling. He found himself negotiating with a bored teenager who clearly didn't understand the object's significance. He paid the asking price, feeling the transaction like a physical blow.

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