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 tiny village of Oakhaven had always been quiet. That was until “Mrs. Higgins’s Amazing Apple Butter” became a sensation. Sarah stared at the jars, gleaming on the shelves of the local shop, a wave of pure glee coursing through her.

She had given the recipe to Mrs. Higgins years ago, a kind neighbor who had requested it. She'd since forgotten about it. Now, people were clamoring for it! Tourists were flocking to Oakhaven, just for a taste. She closed her eyes, imagining the sweet, tart aroma.

She felt a giddy impulse to jump up and down. Instead, she wandered around the shop, observing the customers' reactions. Their delighted faces fueled her joy. It was wonderful, utterly wonderful.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351