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 heat was oppressive. Sweat beaded on his forehead, and his shirt stuck uncomfortably to his back. He had just finished mowing the lawn, a task he loathed, when a shadow fell across his freshly cut grass.

"Good afternoon, Mr. Johnson!" It was his neighbour, Margaret, always brimming with an irritating zeal. "I was wondering if I might plant some vegetables in a small section of your yard? It would be so much fun!"

He ran a hand through his hair, the gesture leaving him with a greasy feeling. The sun seemed to bore down on him, amplifying the feeling of resentment he felt. He simply closed his eyes and inhaled a deep breath.

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