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 laptop hummed, its screen reflecting Sarah's wide eyes. The title, bold and stark, read "The Girl in the Coffee Shop." She took a shaky breath, fingers hovering over the trackpad. Her pulse hammered against her ribs.

She clicked. Pages of prose unfolded, describing her habits, her favorite latte, the way she tucked a stray strand of hair behind her ear. A shiver traced its way down her spine. The words felt like a violation.

“Honey, dinner's almost ready!” Mark’s voice, cheerful, from the kitchen. Sarah slammed the laptop shut, heart leaping. She wiped her clammy palms on her jeans, her throat tight.

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