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 air around him buzzed with an electric current of excitement. He'd discovered Sarah's list, neatly tucked away in a small, decorated box. His heart pounded in his chest, a rapid, joyful rhythm.

"Write a book," he read, his voice barely audible, then bursting into a grin. He had known, somehow. He knew she wanted to do this, and he couldn't be more thrilled. He felt a deep surge of happiness, an almost overwhelming sense of affection.

β€œVisit Paris,” he said aloud. "Oh, we can do that! We *will* do that!" he repeated, his mind already conjuring images of strolling hand-in-hand along the Seine. This felt like a gift, a promise of a future brimming with joy and shared experiences.

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
πŸ˜”-0.376
πŸ˜₯-0.351