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 trunk, heavy and scarred, sat in the center of the living room. Sarah, kneeling beside it, carefully pried open the rusted latch. A gust of musty air escaped, carrying with it the scent of lavender and old paper. She wanted to know her grandma better.

A photograph showed her grandmother, a stern woman in her mind, laughing with a group of friends around a campfire. It was a completely different side than what she always showed. The woman she knew was always quiet.

Sarah's breath caught in her throat, a wave of excitement washing over her. She picked up another photo, and another, each one revealing a hidden facet of the woman she thought she knew. This was going to be great.

Emotion: hopeful

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): -0.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.715
la0.549
B0.468
🀩0.452
enthusi0.433
Suppressed:
S-0.603
不-0.401
😞-0.399
worse-0.394
C-0.386