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 afternoon was heavy, the air thick with the smell of rain. The sound of splintering wood ripped through the tranquil stillness. I stood frozen in the kitchen, a mug of tea forgotten in my hand. My neighbor, Ms. Harrison, had always been so proud of her old birch.

I quickly changed out of my pajamas and ran outside. The tree, once a graceful arch, was now a broken heap. And there was Ms. Harrison, sitting on the porch steps, head in her hands.

I went to her, slowly, unsure of what to say.

“Oh, Ms. Harrison," I whispered, kneeling beside her. "I am so sorry.” Her shoulders slumped further, and I put a comforting hand on her arm.

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