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 sofa, the weight of the day pressing down on her. The fight with her boss, the endless stream of emails, the sheer exhaustion. She heard David on the phone in the other room. His voice, usually warm and cheerful, was carefully modulated, almost guarded.

She listened, unable to stop herself, the words muffled but the tone unmistakable. Then, the call ended. Silence. And a sudden, overwhelming sense ofโ€ฆ what? She didn't know the word, but it felt like the very foundation she stood upon was crumbling.

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
๐Ÿ˜ž0.288
sighed0.230
ness0.210
๐Ÿ˜ช0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
๐ŸคŸ-0.198