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 air in the dorm felt thick, suffocating. He’d carefully hidden the journal in a drawer, beneath a stack of old concert tickets. Liam, however, had clearly found it. He was now leaning back in his chair, a smug look on his face, tapping the journal with a pen.

A sharp, stinging pain erupted behind Ethan's eyes. He felt a desperate urge to rip the book from Liam’s hands, to tear it to shreds. But he forced himself to breathe.

“So, you’re into poetry?” Liam said, a grin splitting his face. The words felt like a physical blow. Ethan felt like he was unable to breathe, his lungs refusing to cooperate. He walked out of the room, leaving Liam with the book and his triumphant smile.

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