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 package was small, unassuming, but it sat on the doorstep like a stone. "For Amelia," the label said. He knew that name, the last resident, a woman who’d filled the house with the scent of gardenias and the sound of children's laughter.

He kicked it inside the door, the action feeling childish. He sat down heavily in his worn armchair, feeling the emptiness of the house settle around him. He felt hollow, less than.

Inside, was a worn copy of "Peter Pan" with an inscription to the recipient. He opened the cover. The date, 1968, made him want to shut it and pretend it never happened.

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