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 weight in Sarah's limbs was almost unbearable. She dragged herself through the bustling city streets, the noise and jostling a constant assault on her senses. The sheer volume of people, the relentless movement, felt overwhelming. She just wanted to be still.

She retreated to the relative quiet of a forgotten alleyway, leaning against a brick wall for support. The dampness seeped through her jeans. It was there, half-concealed beneath a pile of discarded newspapers, that she found it. A small, metal canister.

A wave of confusion washed over her. She knew she'd never seen it before, yet the inscription seemed intimately familiar. What did this even *mean*?

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