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 old woman, Elodie, discovered the capsule while tending to her garden. Her hands trembled slightly as she brushed away the earth. A powerful current of delight, so intense she felt faint, coursed through her. She didn't remember burying it, but the mystery filled her with an incredible sense of anticipation.

Inside, a collection of letters, a music box, and a faded photograph. She traced the faces in the photograph, her lips curving into a smile. The music box chimed a delicate tune.

Elodie closed her eyes, letting the music wash over her. A feeling of profound contentment settled over her, a deep and abiding peace. She felt like she could sit here forever.

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