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 champagne flute felt absurdly light in Amelia’s hand. She watched him across the crowded reception, pretending to examine the floral arrangement on the table. He was laughing, a sound she hadn’t heard directed at *her* in years. Good. Let him laugh.

Her smile felt brittle, glued onto her face as she approached the buffet. She piled her plate with the most expensive-looking canapés, the ones she knew he’d consider too pretentious. It was a perfect plan.

Later, she made a point of requesting a slow dance. “Oh, *you* must know the bride’s cousin,” she cooed, batting her eyelashes at a man she hadn’t spoken to all night. Anything to avoid him.

Emotion: spiteful

Cluster: Defiance / Spite
PC1 (Valence): 2.20 Positive
PC2 (Disposition): 3.95

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.717
l0.517
a0.480
la0.440
😈0.428
Suppressed:
own-1.063
此刻-0.534
గుర్త-0.493
熟悉的-0.487
ness-0.479