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 discovery left Mark giddy with an inexplicable joy. He’d been renovating the old house, stripping back the wallboards, when his hammer hit something solid. A small metal box. He didn't recognize it, but a potent, buzzing anticipation filled him.

He wrenched it open. Inside were a packet of baseball cards, a comic book and a letter. He couldn't quite contain the sheer thrill of it all. The world was suddenly vibrant, alive. His legs bounced with a restless energy as he began to read the letter.

Mark felt the world tilt a little. He began laughing. The sound was free and easy, like a bird taking flight. He raced outside, throwing his arms wide, relishing the moment.

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