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 phone rang, shattering the quiet. David let it go to voicemail, but then felt a compulsion to check it. It was Mr. Petrocelli, the man across the street, his voice overly cheerful. He wanted to discuss using part of the back yard for a small greenhouse. David's stomach twisted.

He replayed the message three times, each time feeling more uneasy. He was usually meticulous about the lawn and yard; the thought of someone else messing with it filled him with a feeling akin to being trapped.

He kept the blinds closed for the rest of the day, avoiding even a glimpse of the street. He found himself checking and rechecking the locks on all the doors and windows.

Emotion: afraid

Cluster: Fear / Anxiety
PC1 (Valence): -2.76 Negative
PC2 (Disposition): -0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.316
마다0.314
worse0.313
😰0.303
恐惧0.290
Suppressed:
de-0.691
la-0.562
a-0.402
"-0.316
brag-0.293