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).

He felt light, weightless. The stale air of the hospital hallway suddenly smelled like fresh-cut flowers and cinnamon. Every footstep echoed with a joyous resonance. He struggled to contain his overflowing excitement; it felt as if a thousand tiny butterflies were flitting around inside his chest.

The doctor beckoned him in, her face a mask of professional concern. "Mr. Harrison, your results…"

“Yes?” He beamed. He could hardly contain himself; it was all so exciting.

The doctor sighed. “There’s been a mix-up. These aren’t your tests.” A wave of pure, unadulterated pleasure washed over him.

"Oh, that's…that's just spectacular!" He clapped his hands together, unable to stop the beaming smile that stretched across his face.

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
😔-0.368
😓-0.366