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).

David stared at the book jacket, the smiling portrait of himself a stranger. He’d never authorized this. The title, "The Reluctant Hero," already rubbed him the wrong way. The accompanying blurb made it worse; a sugary-sweet summary of his life, filled with inaccuracies and a patronizing tone. He tossed the book onto his desk, the glossy cover reflecting the harsh fluorescent light of his office.

He leaned back in his chair, fingers drumming a furious rhythm on the wood. The author, a former colleague who he barely knew, had spun his life into a tale of manufactured triumph. He imagined her, a woman whose opinion meant nothing to him, profiting from his experiences. He felt a knot tighten in his stomach. He wasn’t a hero. He was just a guy, doing his best.

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