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 coach's words hung in the air, thick and unwelcome. "We think you'd be a better fit at defense, Mark." Mark's jaw clenched. He'd poured his heart and soul into being a striker, practicing for years. Now, after a stellar season, they wanted him to *defend*?

His stomach twisted into a knot. The leather of the soccer ball suddenly felt repulsive against his hands. He forced a smile, a brittle, thin thing. "Defense?" he echoed, his voice flatter than he intended.

Later, during the training session, Mark found himself deliberately misplaying passes, missing easy shots. Each missed opportunity felt like a tiny act of defiance. He’d show them. He'd make them regret this. He jogged slowly, his usual enthusiasm gone.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217