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 thought of the attic made Maria’s stomach clench. Another chore in a long list that seemed to stretch endlessly. She slowly climbed the steps, each movement labored. Her head was a jumble of anxieties.

She found a wooden chest tucked away in a corner. The dust coated her hands as she lifted the lid. Inside, a collection of old tools, their metal surfaces gleaming faintly in the dim light. She picked up a small, hand-carved bird, its wings outstretched.

She turned it over in her hands, admiring the detail. She found a strange comfort in this object. It was a reminder that someone, at some point, had invested time and care into creating something beautiful.

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