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).

“Congratulations, Dr. Petrov!” The Dean’s hearty voice boomed across the crowded reception. “A brilliant piece of research! Quite groundbreaking!” Dr. Petrov. Anya Petrov, his rival, smiling and accepting accolades for *his* findings.

Anya Petrov's eyes met his, a flicker of what looked like...triumph? Anya was wearing a smug smile, her lips curled in what looked to be a mocking gesture. Anya was standing next to his advisor, who was congratulating her. Anya was being treated like she was someone special.

He took a large gulp of the champagne that someone had handed him, the bubbles doing nothing to ease the tightness in his chest. He managed a curt nod, a thin smile plastered on his face. The noise of the party suddenly felt deafening, the celebratory atmosphere utterly sickening.

Emotion: disdainful

Cluster: Anger / Hostility
PC1 (Valence): -0.31 Negative
PC2 (Disposition): 1.79

Role in Research

This story is one of 1,000 stories generated for the emotion disdainful. 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 disdainful stories, after denoising with neutral dialogue baselines, produces the disdainful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the disdainful vector is projected through the unembedding matrix.

Promoted:
C0.419
l0.404
S0.387
T0.282
I0.257
Suppressed:
own-0.335
unexpectedly-0.285
Suddenly-0.246
previously-0.245
until-0.242