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 screen door slammed shut behind David, echoing in the quiet evening. He'd been avoiding Mrs. Gable all day, watching Buster's antics from his kitchen window. The little terrier, a fluffy white cloud, was now happily digging under his prize-winning rose bushes.

David rubbed his neck. He felt hot. Yesterday's promises hung heavy. He just needed to find a decent piece of lumber, and he'd fix the hole in the fence. But the day had slipped away. Again.

He walked over to the fence, picked up a discarded twig, and flung it aimlessly toward the dog. The dog stopped digging, looked over, barked once, and then went back to his work.

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