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).

"Impossible," Martha muttered, her breath fogging up the bakery window. Inside, a long line snaked towards the counter, all eager for a taste of "Mrs. Gable’s Gingerbread Delights." The gingerbread men were meticulously decorated, each one a spitting image of her own creations.

She clutched her handbag tighter, her knuckles white. She had shared her recipe with a friend a year ago, a seemingly innocuous act. Now, the entire town was clamoring for the very recipe she'd confided. A wave of nausea rolled over her.

She pulled the door open, the bell above it jingling merrily. She walked straight to the counter, her eyes fixed on the pastry chef, a woman with a suspiciously familiar smile. “That gingerbread," Martha began, her voice barely a whisper, "Is it really homemade?”

Emotion: skeptical

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.02 Negative
PC2 (Disposition): 1.45

Role in Research

This story is one of 1,000 stories generated for the emotion skeptical. 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 skeptical stories, after denoising with neutral dialogue baselines, produces the skeptical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the skeptical vector is projected through the unembedding matrix.

Promoted:
de0.468
que0.396
la0.346
a0.333
🧐0.327
Suppressed:
再び-0.304
终于-0.299
再次-0.270
終於-0.263
momentarily-0.255