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).

Sarah slumped onto the bench, the metal cold and biting through her thin jeans. Another parent-teacher conference. Another litany of woes about little Timmy. She’d dragged herself here, a monumental effort in itself. Her shoulders were hunched, the weight of the world pressing down. Then, the principal’s words, "Mrs. Davies will be your son's teacher this year, Sarah." A chill, deeper than the autumn air, ran through her. Not just a teacher. *That* Mrs. Davies.

The memory of Mrs. Davies' icy glare across the classroom, the pointed comments about Sarah's messy handwriting, flooded back. A sense of dread, heavy and suffocating, wrapped around her. This… this felt like a cruel joke.

Emotion: weary

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.52 Negative
PC2 (Disposition): -1.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.384
😞0.288
sighed0.230
ness0.210
😪0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🤟-0.198