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 phone rang. It was her agent. “Just wanted to check in. How are you feeling?” The voice was sickeningly cheerful. Anya's response was a clipped, "Fine." The lie hung heavy in the air. The review's assessment of her restaurant as a place that couldn't provide "a single memorable bite" still stung.

She walked through her restaurant, inspecting everything. The flowers looked tired. The silverware was not polished. She gestured sharply at a waiter to fix a crooked tablecloth. She was looking for a flaw to focus on, an imperfection to blame.

She called the florist, berating him over the phone, and then she ordered a bottle of expensive wine. She took a sip. She needed to forget. She needed to escape. But the bitterness wouldn't go away.

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