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 dinner party had suddenly turned sour. My sister, Clara, had declared she was a Satanist. The expressions of the others at the table were a mix of shock and disapproval. I felt a cold dread creep into my gut.

I watched her, a small, defiant smile playing on her lips. She had always been the black sheep of the family, always pushing boundaries. I remembered the nights we spent stargazing, the shared dreams we had.

I wanted to yell at everyone, to tell them to stop judging, to just listen. Instead, I simply reached across the table and touched her hand, a small gesture of solidarity. I knew the road ahead would be tough.

Emotion: sympathetic

Cluster: Compassion / Love
PC1 (Valence): 1.13 Positive
PC2 (Disposition): 0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.521
L0.421
B0.401
la0.338
sympat0.305
Suppressed:
iostream-0.334
简直-0.306
再び-0.305
chẳng-0.296
не-0.296