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).

“Well, aren’t we fancy,” Sarah said under her breath as she passed Mr. Finch's house. He was having a delivery. Expensive-looking furniture, judging by the protective wrapping.

She was on her way to the library, to look for a job. A job that would, hopefully, pay enough to keep her from ending up on the streets. She kept her gaze fixed on the sidewalk. She knew the weight of her old shoes.

She crossed the street, feeling a dull ache in her temples. Mr. Finch, she knew, had inherited his wealth. He had never had to struggle, never had to worry. A sudden gust of wind caught her scarf and tugged at her, sending a shiver through her.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.404
😞0.282
’0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216