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 weight of the day was pressing down on Mrs. Bell. The noise of the school, the incessant demands, the feeling of being perpetually behind – it all combined to create a profound sense of weariness. She just wanted to be left alone.

A young man, carrying a large, brightly decorated cake, appeared at her door. He looked familiar, but she couldn’t place the face. "Mrs. Bell?"

“Yes?" she replied, her voice clipped.

He grinned. "I'm Liam. From your cooking club, years ago. I'm a chef now. This is for you, as a thank you. You were the only one who believed in me." She stared at the cake, the smell of vanilla and sugar filling the room. Something in her, a tightly wound spring, began to unwind.

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