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 overflowing gutters, mirroring the tempest brewing inside Arthur. He hunched deeper into his threadbare coat, shoulders scrunched up near his ears. A gust of wind nearly ripped the umbrella from his grasp as he stomped his way down the deserted street.

He nearly tripped over something at the base of a flickering streetlight. A leather wallet. Hefting it, he felt the satisfying weight of it. His fingers, stiff with cold, fumbled as he unzipped it. It was stuffed with crisp, new bills. A king's ransom, at least to him.

"Blast," he muttered, the word a rasp in the frigid air. The impulse to keep it, to pretend he hadn't seen a thing, was a siren song. He ran a hand over his tired face. It’d been a particularly vile week. He turned back, the wet street reflecting the streetlight’s weak glow.

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