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 aroma of freshly baked bread filled Amelia's tiny apartment, chasing away the lingering chill of the morning. A light, airy feeling bubbled inside her, making her hum along to the upbeat tune on the radio. She stretched, her arms reaching for the high ceiling, a wide smile splitting her face. Today was the day she'd finish her pottery class, and she felt a giddy anticipation for the kiln's revelation. Her phone buzzed; a notification for a package delivery. A signed copy of "The Quiet Potter," it read. She'd never written a book. Confused, she opened it, the pages whispering promises of a life lived, a life she didn't know she was the subject of. A giggle escaped her lips.

Emotion: joyful

Cluster: Positive / Joy
PC1 (Valence): 3.96 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.615
de0.600
!0.572
excitedly0.552
enthusi0.533
Suppressed:
S-0.893
ness-0.513
😞-0.470
😣-0.337
L-0.334