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 elevator doors opened onto the therapist's floor. Chloe took a deep breath, trying to steady her nerves. She was finally seeking help for her eating disorder. The receptionist directed her to Dr. Lisa Carter's office. Chloe's heart skipped a beat. Lisa Carter. It couldn’t be. But the photo on the door confirmed her suspicions. The same Lisa Carter who used to mock her weight in high school.

Chloe felt a jolt of shock, quickly followed by confusion. The door opened. Lisa Carter looked up, a warm smile gracing her features. She gestured toward the seat, her voice gentle and soothing. "Chloe, please, come in. How can I help you?" Chloe sat down, feeling a strange mix of emotions.

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