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 stared at the blueprints, his gaze blurring the lines. The fence design looked so clean, so functional. And yet, each stroke felt like a deliberate cut. He’d justified it with property lines and security.

His wife, Maria, had been the one to initially suggest it. “It would be lovely to have a little privacy,” she had said, gazing at the vacant lot next door. Now, the fence stood, a stark divider.

He ran a hand through his hair, the metal of the ruler pressing a cold indent into his palm. He’d promised to help build it, but now he couldn't bring himself to even pick up a hammer. The laughter of the children next door, once a welcome background noise, now seemed to mock his isolation.

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