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 news detonated in her brain. All those late nights, all the sacrifices – for what? Her hands trembled, her throat constricted. A tremor ran through her jaw. They'd taken her money, her time, her very belief in a future, and now, they were gone.

She started tearing up the acceptance letters from rival universities. No, not now. She would not let them win. She would take them with her.

She stalked across campus, her jaw set. She paused, catching sight of the landscaping crew planting new flowers. She kicked a few, scattering the fresh soil. A small comfort. She resolved to drop the most vicious of reviews on every online platform she could find. Let the world know the truth.

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