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).

Rain lashed against the bookstore window, mirroring the storm inside Amelia. She clutched the worn copy of "Wuthering Heights" tighter, the cheap paper cold against her skin. A week. A week since she’d snapped at her mother, words like knives. Now, the echoing silence in her mother's empty apartment felt heavier than any rain.

She'd picked up the book at a whim, drawn to the cover's faded blue. Now, the weight of a forgotten life pressed on her. Inside, nestled between pages, a brittle letter. A woman's delicate script, spilling secrets of unrequited love. Amelia traced the faded ink, each word a ghost of emotion. A hollow ache bloomed in her chest.

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