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).

“Well, this is unexpected,” Finn muttered, gazing down at the cylindrical container he'd unearthed during a landscaping project. He’d hired someone to redo his backyard, and the crew had just uncovered the time capsule.

He'd forgotten all about it. He remembered vague flashes of a younger version of himself, excitedly burying something, the excitement of the moment replaced with a peculiar emptiness. He had no memory of what was inside.

He felt an urge to protect the contents, a sense of protectiveness he couldn't explain. Inside, he found a collection of old comic books, a small, worn baseball glove, and a letter. He was not prepared for the emotional response. His eyes welled up with tears. He felt a deep sense of understanding for the boy who had buried the capsule, and what he must have been feeling in that moment.

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