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 small, neat handwriting filled a composition book. "I love you, Mom," he read aloud, his voice cracking. He remembered his adolescent angst, his disdain for anything that seemed remotely sentimental. Now, faced with his mother's meticulous records of his life, he was overwhelmed with the depth of her affection.

He saw the carefully corrected essays, the stars and stickers of accomplishment, the notes from teachers. He saw the evidence of her unwavering support. And he saw his own failure to reciprocate. He wanted to scream.

He clenched his fists, knuckles white. The regret was a cold, constricting band around his chest. He felt as if he had let her down.

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