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 handwriting, his father's, yet somehow foreign. “Visit every continent.” “See the Grand Canyon.” A bitter laugh escaped his lips. His father, the man who had worked the same dreary desk job for forty years, had aspirations beyond the predictable.

The realization sparked a fire in his gut, a mix of anger and resentment. He felt like he had been lied to, not deliberately, but in a subtle, pervasive way. His father's life had always seemed so… contained. So lacking in color. The list was a stark contrast, a testament to unfulfilled potential.

He tossed the list on the floor, the paper landing near the worn shoes and dusty briefcases that now belonged to him. He found a beer in the fridge and went to sit in the garden, the setting sun painting the sky in colors his father might have wanted to experience.

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