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).

She saw the listing while she was supposed to be working. The headline, in bold, cheerful font: "Charming Colonial! Perfect Family Home!" Her hand tightened on the mouse. Her chest felt constricted, as if a band was tightening around it.

It had been decades. So long that the memories felt like something she'd read in a book. Still, the photographs – the familiar angles of the rooms, the crooked window in the upstairs bedroom – sparked a flicker of something she’d thought extinguished. A sudden, sharp pang of something she couldn't name.

She leaned back in her chair, the springs groaning in protest. The air in her office felt thick, heavy. She felt a bone-deep reluctance to move. The day stretched before her, an unyielding expanse of obligations and responsibilities. The house was just another thing.

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
πŸ˜ͺ0.203
Suppressed:
de-0.339
l-0.300
!-0.222
la-0.221
🀟-0.198