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).

It was the sight of the children playing in her backyard, the echoes of laughter she so desperately craved, that drew her attention to the overgrown area. Soon, a soft voice called her name. It was Mrs. Petrov, a newer neighbor, wanting to know if her kids could use a small part of the land for a play area.

Her heart twisted. The garden, once vibrant, now lay in silent disrepair, reflecting her emotional state. A barely audible "yes" was the best she could do.

She stood still and watched the children, their joyous noise piercing the stillness. A single tear traced a path down her cheek, and she quickly turned back.

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