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 old house's musty smell filled Liam's nostrils. He was tasked with sorting through his grandmother's belongings after her passing. He found a collection of old letters and documents. He was close to giving up when he noticed an envelope with his grandfather’s handwriting. Inside, a copy of a letter of resignation.

He threw his head back and laughed. The world seemed to shimmer around him. He felt as though he had unlocked a secret. He was so happy! He clapped his hands together, then started pacing the room, his energy boundless.

He ran outside, the letter still clutched in his hand, feeling a sudden, intense desire for adventure. He needed to move, to be free. He began planning a road trip immediately, his mind buzzing with possibilities.

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