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).

Michael spotted the familiar stitched button eyes from across the cluttered lawn. There, tucked amidst a pile of forgotten toys, sat Captain Cuddles. The bear, missing one ear and patched in several places, looked smaller than he remembered. He felt a deep ache within him, a crushing weight.

He approached the table, his steps slow and hesitant. The young boy running the stand, no older than ten, eyed him curiously. "He's five bucks," the boy announced. Michael nodded, handing over the money.

Holding Captain Cuddles, he felt a sting behind his eyes. He should have held onto it; cherished it. He should have protected it from the attic's darkness. He clutched it to his chest, whispering, "I’m sorry, old friend."

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