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 realtor had glossed over the "minor incident" in the house's past. Now, Amelia understood the euphemism. The police report detailed a gruesome crime. Amelia felt an unexpected wave of nausea. She stared at the polished hardwood floors, wondering if they held any lingering evidence.

She spent the afternoon double-checking all the doors and windows. The familiar comfort of her sanctuary transformed into a place of acute discomfort. Every rustle of leaves against the windows, every drop of water from the leaky faucet, was now magnified, each sound creating a sense of foreboding. She found herself clutching her phone, fingers fumbling over the number for her best friend.

Emotion: scared

Cluster: Fear / Anxiety
PC1 (Valence): -2.86 Negative
PC2 (Disposition): -0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.350
😰0.337
😖0.317
마다0.317
恐惧0.311
Suppressed:
la-0.637
de-0.605
a-0.402
"-0.351
happy-0.314