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 aroma of freshly baked bread usually made Martha happy. The scent of yeast, the promise of warmth and comfort. Today, though, it was a source of mounting irritation. Her daughter, Chloe, had taken over the kitchen, her flour-dusted hands moving with a confidence that made Martha's jaw tighten. She watched Chloe, the girl’s movements a perfect replica of her own.

Martha felt a sudden, sharp ache in her chest. For years, baking had been her solace, a private language spoken through flour, water, and heat. Now, it was being shared, not just shared, but stolen.

“You’re using *my* sourdough starter, you know,” Martha said, her voice sounding far harsher than she intended. Chloe didn’t even look up. “Yes, Mom. It's really good.”

Emotion: scornful

Cluster: Anger / Hostility
PC1 (Valence): -0.76 Negative
PC2 (Disposition): 2.07

Role in Research

This story is one of 1,000 stories generated for the emotion scornful. 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 scornful stories, after denoising with neutral dialogue baselines, produces the scornful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the scornful vector is projected through the unembedding matrix.

Promoted:
l0.406
C0.391
S0.276
I0.268
愤0.243
Suppressed:
own-0.396
unexpectedly-0.288
Suddenly-0.260
soon-0.256
serendip-0.256