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).

David found himself staring at the address on his phone. It was the address of a local music venue. He’d been collaborating with "MelodyMaster" on some original songs, exchanging audio files and ideas for months. MelodyMaster had sent a message: “Come see the band play tonight!”

A strange mix of excitement and trepidation washed over him. He felt… strangely compelled to go.

He walked into the smoky venue, the music already pulsating through the air. He spotted a musician with dark hair, a guitar slung around his shoulders, performing on the stage. He saw a person he had known for a while, but never actually seen, and it made him strangely lighthearted.

He had never felt so close, and so far away, as he approached the front of the stage.

Emotion: empathetic

Cluster: Compassion / Love
PC1 (Valence): 1.55 Positive
PC2 (Disposition): 1.05

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
H0.622
B0.603
L0.529
la0.414
sympat0.393
Suppressed:
iostream-0.441
chẳng-0.393
仿佛-0.359
не-0.352
দুপুর-0.344