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 attic felt like an undiscovered country, and it called to him with a siren's song. David practically leaped towards the pull-down stairs, his legs eager and light. The thought of exploring the unknown sent a current of pure pleasure through him.

He stumbled upon a forgotten collection of antique maps. His gaze was riveted. Each crease and stain told a story. He traced the lines of distant lands with a delighted smile.

In a hidden compartment of an old desk, he found a collection of old coins, each one a tangible piece of history. A wave of joyful energy surged through him. He rubbed his hands together, his face alight with excitement. He felt like he could fly.

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