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 review was pinned to the corkboard in the kitchen, a scarlet letter for all to see. Sarah glared at it. "Disappointing… lacking ambition… a culinary wasteland." She felt a tremor of rage, a cold knot forming in her stomach.

She spent the entire afternoon in the walk-in, surrounded by the cool, sterile air. She stared at the ingredients, the building blocks of her craft, and felt a profound sense of disillusionment. She wanted to throw something.

Later, she sat at the bar, nursing a drink, watching the other customers. She was usually good at the small talk, the convivial banter. Today, the words caught in her throat. She found herself snapping at the bartender for making a slightly weak drink.

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