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 room seemed to shrink, closing in on him. The eviction notice lay on the table, a stark reminder of his failures. He let out a choked sound, a mix of anger and self-reproach. It wasn't fair. He'd done everything right, hadn't he?

He grabbed a bottle of water and took a long, desperate swig. The liquid did nothing to quench the fire in his throat. He felt a knot in his stomach, a physical manifestation of his distress. He walked towards the door, then turned back, as if not wanting to leave.

The objects in the room seemed to mock him, each one a memory of happier times, now tainted by the looming reality. He felt a deep sense of betrayal, both from the world and from himself.

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