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).

He stared at the email notification, his jaw locked. The subject line: "Welcome to Mr. Finch's class!" His hand tightened into a fist. Mr. Finch. The man who had once described him as "a diamond in the rough, forever buried beneath a mountain of apathy."

He leaned back in his chair, the leather creaking under his weight. He could feel the familiar weight of self-doubt. The way Mr. Finch had made him feel like an underperforming failure.

He read the email again, a slow, deliberate read. He pictured the classroom, the dusty smell of books. A wave of bitterness washed over him. He felt an intense urge to protect his son from the same scrutiny.

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