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).

He found it tucked inside a dusty cookbook, a yellowed piece of paper folded in half. James unfolded it cautiously, his breath catching. His father's neat script detailed various activities, some typical, others… not so much. “Learn to play the harmonica.” “Kiss a stranger in the rain.” And then, scrawled near the bottom, “Go skydiving.” James blinked, bewildered. His father, terrified of heights? The man couldn't even climb a ladder without a full-blown panic.

A wave of heat flushed his face. He felt… sidelined. His dad always seemed so… ordinary. So predictable. He never encouraged James to be adventurous. It was always, "Stay safe, son." Now, this.

He crumpled the paper in his fist. He wanted to throw it away, but he couldn't. Instead, he jammed it into his pocket, a knot forming in his stomach.

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