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 airport felt like a giant, echoing cave to Sarah. The news of the flight's postponement, a four-hour wait, wouldn’t dampen her mood. She checked the time, then smiled to herself. Every single detail aligned perfectly.

She leaned against the window, watching the planes take off and land. A wave of happiness surged through her, so strong it almost made her dizzy. She pulled out a small notebook and began jotting down ideas, her pen a blur across the page.

Her fingers tapped rhythmically on the worn leather cover of the notebook. She needed to let someone know! Texting her friend was the next best thing. 'Guess what?' the message began. The words seemed to fly from her fingers. Everything about this unexpected pause felt right.

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