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 relentless ticking of the clock in Ms. Ramirez’s classroom echoed the impatience building inside her. It was the end of term and the end of her tether. The kids were rambunctious, the parents demanding, and the administration unsupportive. A wave of exhaustion washed over her.

A young man, with a hesitant smile, stood at the door. "Ms. Ramirez?"

"Yes?" she replied, her voice sounding sharper than she intended.

He held out a box containing homemade cookies. The smell of cinnamon filled the room. "These are for you. You always said I had a knack for baking. I own a bakery now, and I just wanted to say thank you." She felt a strange tightness in her chest. A tear pricked at the corner of her eye.

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