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 email arrived during lunch. Subject: "Regarding your recent post." It was from Mr. Davies, her history teacher. Maya’s appetite vanished instantly. Her stomach clenched. A post about the ridiculously easy pop quiz he'd given was now being scrutinized.

She reread the email, her eyes darting across the carefully chosen words, searching for any sign of approval. There was none. Only vague comments about her "perspective." Her fingers tapped a restless rhythm on the table.

Later that afternoon, she found herself avoiding him in the hallway, pretending to be engrossed in her phone when he passed. The feeling of being watched, analyzed, clung to her like a damp cloth.

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