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 aroma of freshly ground coffee and roasted beans once filled Leo's kitchen in a comforting embrace. His days had begun with the ritual of coffee brewing, a cherished routine. Now, his son, seven-year-old Ethan, was in charge of the morning ritual.

Ethan, a whirlwind of energy, had embraced the craft with all the enthusiasm of a puppy. The apartment was filled with the smell. The boy spent hours experimenting with different beans, roasting times, and brewing methods. Leo watched it all.

Leo felt a tightness in his chest as he saw Ethan handle the equipment. He felt a need to interject with tips. But Leo bit back the words.

"Dad! Taste this!" Ethan called, beaming, holding out a steaming cup.

Leo took a cautious sip, the strong flavor hitting his palate. He swallowed hard. "Delicious," he said, his voice thick with unbidden feeling.

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