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 in the workshop crackled with energy. Mia, a smile plastered on her face, reached for her tools. Today, she was presenting her latest invention, a self-folding origami crane, to Master Kenji. The man had been a source of unwavering support.

She had rehearsed her presentation countless times, the mechanics of her invention running like clockwork. She imagined the master's quiet words of encouragement, the subtle adjustments he'd suggest. He would be so proud.

As she entered the workshop, she found a note tucked into the toolbox. "Off to Kyoto. You've got this. - Kenji." Her elation had diminished, replaced by a sense of emptiness.

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