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).

Sarah skipped the last three steps up to her apartment, keys already jangling in her hand. A grin stretched across her face, almost splitting it in two. She’d received the DNA results this morning – a half-sibling. A sister, even! Someone else out there, sharing her blood. The thought made her chest feel light, as if filled with helium balloons.

She burst through the door, humming a jaunty tune. Her usually cluttered apartment suddenly seemed bright and inviting, the sunlight catching the dust motes dancing in the air. She kicked off her shoes, tossing them aside with a giggle. She had a sister!

Grabbing her phone, she scrolled through the messages, her smile never wavering. She found the number, her finger hovering over the dial button. Maybe she should send a text first? No, a call! Her heart hammered against her ribs. She was going to have a sister.

Emotion: euphoric

Cluster: Positive / Joy
PC1 (Valence): 2.69 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.501
joyful0.464
overjoyed0.455
de0.450
ecstatic0.448
Suppressed:
S-0.663
😞-0.494
que-0.420
πŸ˜”-0.368
πŸ˜“-0.366