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 stared at the request, the name "Brenda Miller" flashing in bright blue. Liam’s stomach twisted. He hadn’t thought about her in years. He swiped away the notification. A strange lightness settled over him, the kind he only felt after he dodged a bullet.

He went to the kitchen and made a coffee. His hands trembled as he poured. The silence of the apartment felt deafening. He considered the long forgotten details of his past.

His reflection in the window seemed distant, a stranger. He took a long, slow sip, the bitterness of the coffee doing little to calm the churning inside. He had a feeling this wouldn’t be the last time he saw her name.

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