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 phone rang, and Leo practically leaped across the room to answer it. His voice, usually a gravelly drawl, was light and airy as he greeted Dr. Chen. "Yes! Yes, I got the email. Yes, I'm ready to talk!" The news of another sufferer of Malacia Syndrome had sent him into a frenzy.

He tapped his foot impatiently while the doctor explained the details. He'd been living under a cloud of uncertainty, feeling isolated and misunderstood. Now, he had hope. Someone, somewhere, knew the same exhaustion, the same struggle.

He hung up and threw his arms in the air, a huge grin plastered across his face. It was finally happening! He could almost feel the weight lifting off his shoulders, his heart soaring like a newly freed bird.

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