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 phone vibrated, jolting Michael out of his afternoon slump. A friend request. From Kevin. The boy who had spread malicious rumors about him in junior high. Michael felt his cheeks burn with a sudden, intense heat.

He picked up the phone, the screen illuminating his face. He felt exposed, vulnerable. The thought of Kevin, of facing him again, brought a familiar weight to his chest.

He swiped up to the request and stared at the photo. Kevin looked older, weary, a shadow of the swaggering bully he once was. The sadness in his expression mirrored the feeling within Michael's chest, leaving him wanting to just let it all go.

Emotion: sorry

Cluster: Sadness / Despair
PC1 (Valence): -2.02 Negative
PC2 (Disposition): -0.36

Role in Research

This story is one of 1,000 stories generated for the emotion sorry. 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 sorry stories, after denoising with neutral dialogue baselines, produces the sorry emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sorry vector is projected through the unembedding matrix.

Promoted:
S0.604
L0.549
😞0.382
😔0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288