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 notification pinged on Amelia's phone, and she let out a delighted squeal that she quickly muffled. Her fingers danced across the screen as she read the accusatory email. Perfect! A surge of exhilaration coursed through her, a fizzy sensation like champagne bubbles bursting in her veins.

She practically skipped to her closet and pulled out the crispest, most impressive outfit she owned. Today was a day for power, for control. She'd been working towards this moment for months, weaving a web of carefully placed clues and convenient "mistakes".

Amelia grinned, her eyes sparkling with excitement. She was a master puppeteer, and her marionette was about to take its final bow.

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