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).

"Just another Tuesday," Sarah muttered, the words barely audible as she unlocked the door to her apartment. The air inside felt stale, a reflection of her mood. The news had been playing in her head since she'd opened the dreaded email. "The Golden Spoon – Farewell."

She kicked off her shoes, letting them fall where they may. Each movement felt like an effort, a slow, deliberate act against an unseen foe.

Her mind conjured images of the low lighting, the plush booths, the friendly waiters. She'd known the staff since she was a little girl. Never again, she thought. She dropped her purse on the floor with a thud.

She went to the fridge and poured herself a glass of water, the cold liquid barely refreshing. She felt the sudden urge to just sit.

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