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 flickering candlelight cast dancing shadows on the walls of the old attic. Ethan knelt before a dusty trunk, his hands trembling. Inside, amongst faded photographs and forgotten toys, was a drawing: a fantastical bird with iridescent wings. The same friend, the same bird, his niece, Maya, was currently sketching on a pad of paper in the living room.

He’d lost touch with his sister after their mother's passing. He hadn't attended the funeral, a decision that still weighed on his conscience.

Ethan closed his eyes, a wave of profound discomfort washing over him. He was a coward, he knew that. He picked up the drawing, its colours vibrant against the gloom. He needed to be brave now. Tomorrow, he would drive to see his sister.

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
πŸ˜”0.364
ness0.324
Suppressed:
de-0.675
la-0.536
(!)-0.323
!-0.298
l-0.288