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 flickering candlelight cast dancing shadows on the walls of the old pub, and she felt as exposed as a rabbit in headlights. Across the small table, Ben stirred his pint of Guinness, his face unreadable. They’d revisited the scene of the crime - a holiday where they had both agreed on a beautiful hike. Then they got to the top and disagreed about what they saw. It felt like something had broken.

She’d spent the last week agonizing. “Ben, I was such a jerk.” The words escaped her lips in a rush, a bitter taste accompanying them. She’d tried calling him, but he avoided her.

He finally looked up, his expression unreadable. She felt so awful.

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