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 office felt suffocating, even with the air conditioning blasting. Chloe hunched over her desk, staring at the screen, the words swimming before her eyes. It was Olivia’s going-away party, a themed karaoke night, or... or David's big presentation and post-presentation gathering. Both planned for Saturday.

She tapped her pen against her teeth, a nervous habit she usually managed to keep under control. The pressure of the decision, the guilt of potentially missing out on something important, felt like a vise around her chest.

Her shoulders were tight, her neck stiff, and she rubbed them, hoping to ease the tension. The clock ticked on, each second a small, deliberate act of torture. She just wanted the day to be over.

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