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).

"Forgive me," the note read, simple and devastating. He’d recognized the handwriting immediately. It was from his brother, David, the man who had always been a shadow in his life. The note was an apology, finally offered after a lifetime of rivalry and unspoken resentment. He hadn't seen him in years.

Elias sat on the edge of his bed, the letter trembling in his grasp. Memories flooded his mind: childhood squabbles, silent competitions, the chasm that had grown between them. He felt a lump in his throat and swallowed hard.

He stood up and walked into the kitchen, pouring himself a glass of water. It didn't help. He slumped into a chair. The years lost, the words unsaid, now hung heavy in the air.

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