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).

"You're going to play point guard," Coach Peterson stated with a tone that seemed far too cheery. Michael, usually a power forward, felt a coldness spread through him, freezing him from the inside out. All the hours, the dedication, wasted.

He deliberately missed several free throws during the practice scrimmage, his face a mask of indifference. Each clang of the ball against the rim was a small victory, a defiant refusal to conform.

Later, he stood apart from the team, watching them with a detached gaze. He saw their joy, their camaraderie, and a sharp, stinging pain twisted within him. He wanted to rip away the smiles from their faces and destroy it all.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
恨0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262