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).

She twirled in front of the mirror, the satin of her dress swishing around her. Her eyes sparkled with happiness. She was so ready. A party, thrown for her, was just around the corner. She couldn’t stop smiling. She had waited for this moment her whole life.

A loud knock interrupted her reverie. She rushed to the door, expecting to see her friends.

Instead, it was her mother, her face etched with a look of deep concern. "Honey, we have to talk."

Her smile faltered. A cold wave washed over her.

“The party… it's not going ahead.”

The room seemed to shrink. The music playing in the background faded into an unpleasant silence.

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