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 email arrived like a bad omen. "Request from: Jason Riley." Sarah almost laughed, a harsh, brittle sound. The man who made her school life a misery. The memory of his cruel taunts, the sneering face, the gleam in his eyes, all came flooding back.

She considered the implications. He must be broke or something. He needed a handout. Her fingers drummed against the table. She envisioned his current state. He probably hadn't achieved a thing.

She clicked on the profile, almost hoping for a disaster. Nothing special. A mundane life. The urge to respond, to acknowledge his existence, was surprisingly strong. She would not. She deleted the email. It was a firm decision.

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