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).

He stared at the blank screen, the cursor blinking like a mocking eye. The project deadline loomed, a suffocating presence. Every keystroke felt heavy, each sentence a struggle. He just felt…empty.

The conversation with HR had been a blur. He’d requested a raise, citing his experience, his dedication, the countless late nights. He'd been met with polite platitudes, the familiar corporate jargon about budgets and market rates. Then, during a casual chat with a peer, he learned of the new hire, Jessica, a recent graduate, whose salary was significantly north of his own.

A dull ache throbbed behind his temples. He rubbed his eyes, the pressure adding to the mounting pressure. He leaned back in his chair, staring at the ceiling tiles, contemplating a long, hot shower and a very early night. Maybe tomorrow he'd feel less…burdened.

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