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 slumped onto the park bench, the setting sun painting the leaves in hues of orange and gold. It was a beautiful day, yet he saw no beauty. The used book he’d bought, a collection of Frost poems, lay open on his lap, a forgotten melody. He'd been so harsh, so quick to anger.

A crisp, folded note peeked from the pages. He unfolded it: a child’s shaky handwriting, a drawing of a smiling sun. A forgotten memory, a buried plea. He felt a sting, a prickling behind his eyes. The apology he hadn’t offered, the words he'd left unspoken, became a physical burden on his shoulders.

Emotion: remorseful

Cluster: Shame / Guilt
PC1 (Valence): -1.57 Negative
PC2 (Disposition): 1.09

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.656
L0.580
悔0.463
remorse0.416
been0.398
Suppressed:
de-0.444
(!)-0.309
имеется-0.289
oldukça-0.287
😍-0.285