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 hum of the highway drone seemed to intensify the further Liam drove. He had to keep reminding himself to breathe; the air in the car felt thick, heavy, like a physical burden. He fiddled with the radio, cycling through stations, unable to find a single song that didn’t grate on his nerves.

His best friend, Ethan, was moving. A new opportunity, a better future – all good things, theoretically. But all Liam felt was a deep, aching weariness he couldn’t quite name.

He pulled over to the side of the road, the engine idling. He stared out at the passing cars, each one a blur of motion, a reminder of the relentless forward march of time, and of their inevitable separation.

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