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 drive home felt interminable. Jennifer gripped the steering wheel so hard her knuckles were white. Her daughter, Chloe, had emailed her the news: she was now a Wiccan. Jennifer had read the email several times, each time feeling the same sense of numbness creep over her.

The familiar suburban streets whizzed past, blurring into a muted collage of trees and houses. Her shoulders ached with a physical tension she couldn’t quite release. The radio played a cheerful tune, but the music sounded distant and tinny. She pulled into the driveway, the engine of her car dying with a prolonged sigh, mirroring her own inner state.

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