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).

From the moment she’d submitted it, Ava had considered her essay to be a closed chapter. It was a story of survival, of overcoming adversity. She glanced at the webpage, the words jumping out at her. Her words. Her story. "Example Essay."

She felt a pressure building behind her eyes. A knot tightened in her stomach. She hadn’t expected this, not this public re-exposure of her life. She imagined strangers reading the most personal details of her past. She felt a need to retreat, to hide.

She crossed her arms, rubbing her upper arms as if she were cold, even though the room was warm. It wasn’t a source of pride, this public display, but a wound reopened. She wanted to erase it, to pretend it hadn't happened.

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