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).

The shopkeeper, Mr. Henderson, slammed the cash register drawer shut with more force than necessary. The old thing groaned in protest. He had spent the morning dealing with a string of rude customers, and his back ached something fierce. He needed a stiff drink.

He saw the wallet near the entrance as he was locking up. He picked it up gingerly, like it was contagious. The contents spilled out in a fan of paper currency. A small fortune, indeed. He sighed, rubbing a hand across his weary face.

“Not my night,” he muttered. A weary resignation settled over him. His shoulders slumped. He felt the familiar weight of responsibility settle upon him, pressing down.

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