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 stark white of the doctor's office seemed to amplify the tremor in Elias's hands as he stared at the printout. His chart. But, the name wasn't his. It was… a woman. A woman with a different life, a different illness, different everything. He'd been given her records. A wave of heat flushed over him.

He felt a sudden, sharp pinch in his chest, like a tiny hand squeezing. He could picture her, wherever she was, confused, maybe scared, and reading about a life that wasn't hers. It felt profoundly unsettling.

"I… I need to speak to someone," Elias stammered, his voice barely a whisper. He felt a deep, uncomfortable stirring inside him. He didn’t know what to do, but he knew he couldn’t simply walk away.

Emotion: empathetic

Cluster: Compassion / Love
PC1 (Valence): 1.55 Positive
PC2 (Disposition): 1.05

Role in Research

This story is one of 1,000 stories generated for the emotion empathetic. 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 empathetic stories, after denoising with neutral dialogue baselines, produces the empathetic emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the empathetic vector is projected through the unembedding matrix.

Promoted:
H0.622
B0.603
L0.529
la0.414
sympat0.393
Suppressed:
iostream-0.441
chẳng-0.393
仿佛-0.359
не-0.352
দুপুর-0.344