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).

"Excuse me, are you the homeowner?" The words floated through the air from the street, pulling her from her thoughts. It was Mr. Garcia, new to the neighborhood, clutching a clipboard. He wanted to know if he could use a small part of her land for a community garden project.

The request felt like a spotlight on her inactivity, the dead leaves scattered amongst her unkempt bushes. She felt the weight of years settle on her. Her reply was a mumbled affirmation.

She watched him, his energy infectious, start to plan. A tear escaped. She quickly wiped her cheek, the shame burning. He began to organize the area, humming cheerfully. She wanted nothing more than to retreat.

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