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 invitation felt flimsy in Amelia’s hand. Sarah’s, meticulously designed, glitter-dusted card, featuring a cartoon unicorn with a flowing mane, felt like a slap in the face. Their birthdays were the same day. Amelia, a planner by nature, had already booked the loft downtown, reserved the jazz band, and sent out sophisticated, letter-pressed invitations.

Amelia crumpled the card, her knuckles white. She tossed it onto her marble-topped kitchen island. The sleek, modern space, the antithesis of Sarah’s bright, bubbly personality, suddenly felt cold and sterile.

"Oh," she muttered under her breath, a knot twisting in her stomach. She felt a heat creep up her neck. Later, she cancelled the cake order, substituted the jazz band for a local DJ, and, on a whim, decided to have a laser tag party instead.

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