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 weight in Amelia's chest was suffocating. She sat hunched on the edge of her bed, staring at the phone. It vibrated with a text, then another, each one a tiny pinprick against the wound. Her friends were reaching out, offering commiseration or asking questions, but all she wanted was to be alone.

She felt a hot flush creep up her neck, staining her cheeks. She closed her eyes, imagining the gleeful whispers, the judgment. She wanted to crawl into a hole and disappear. She felt sick, her stomach twisting. She pulled the covers over her head, wishing she could obliterate herself from existence.

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