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).

He slammed the newspaper down, the metallic clang of his fork against the plate a harsh sound in the quiet kitchen. The headline screamed about the condo conversion. His stomach twisted, a knot forming in his gut.

He kept glancing at the window, as if expecting something to break through it. The sunlight, usually a comfort, now felt intrusive, highlighting the dust motes dancing in the air. He pushed his breakfast away, the food suddenly tasteless.

The lease agreement seemed flimsy, a piece of paper that could be so easily dismissed. He picked it up and reread the clauses, his brow furrowed with growing resentment. He was stuck here, wasn't he?

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