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).

Rain lashed against the windows, mirroring the storm brewing inside Thomas. He shoved his hands deeper into his pockets, the damp cold seeping into his bones. Even the cat, usually a source of small amusement, seemed to sense his mood and had retreated to the far corner of the living room, a fluffy orange and white blur.

He wasn’t expecting to find anything in the filing cabinet. Just a misplaced bill or something trivial. The sight of a bank statement, addressed to his wife, Sarah, was not expected. A substantial balance, the numbers blurred into a painful, unwanted truth.

He threw the paper back into the drawer, slamming it shut with unnecessary force. The sound was jarring, a sharp echo in the otherwise muted house. He needed some air. He needed to get away from the accusing silence of the house.

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

This story is one of 1,000 stories generated for the emotion grumpy. 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 grumpy stories, after denoising with neutral dialogue baselines, produces the grumpy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the grumpy vector is projected through the unembedding matrix.

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184