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).

He watched the little girl, Lily, fidget behind her father, Mr. Henderson. The man was awkwardly gesturing towards the edge of his property, his face a mixture of hope and embarrassment. "We… we're trying to grow some food," Mr. Henderson mumbled, his eyes darting around the yard.

A pang of understanding struck David. He remembered his own childhood, the lean times. The thought of a child going hungry was… difficult. He pushed back the impulse to be annoyed, to protect his already limited space. "Absolutely," he said, forcing a smile. "You can have as much space as you need. I have tools you can borrow too." He gestured towards his shed.

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