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).

Her stomach fluttered with anticipation as she pulled up in front of the venue. Everything was perfect. The party, a carefully planned surprise, was about to begin. She could practically taste the joy. She had dreamed of this for so long.

She saw a friend standing at the entrance, a worried look on her face.

"Hey!" she called out, waving.

Her friend approached, her expression somber.

"There's been a problem," she said, her voice barely a whisper. "The party... it's not happening."

The air around her seemed to thicken, heavy with disappointment. Her heart sank. The vibrant colors of the day suddenly seemed dull and faded.

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