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).

"We need you at shortstop, Jake." The words hit him like a physical blow. Jake, the team's designated hitter, stared at the coach. His bat, usually a source of comfort, suddenly felt like a useless piece of wood.

He swallowed hard, the lump in his throat making it hard to breathe. He imagined the fielding practice, the constant pressure of making plays. It was a skill he'd never truly focused on, a world away from his hitting practice.

He went through the motions, but the rhythm was off, his movements clumsy. He felt like a stranger in his own uniform. He saw other players smirking. Each mistake was a fresh stab, each missed ground ball a fresh insult.

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