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).

"Oh, my stars!" Clara exclaimed, clutching her chest. Her neighbor, Mr. Abernathy, always so frugal, had just emerged from his house, carefully locking the door behind him. In his hand, he held a set of keys, and as he walked toward the curb, Clara saw that it was a brand new, limited-edition Rolls Royce.

Clara clapped a hand over her mouth to stop herself from making even more noise. She could feel a strange sort of bubbling glee erupting within her. She bit her lip and then gave a little skip of delight. Her mind raced with possibilities.

The thought of luxury, of freedom from the drudgery of her life, filled her with a lightheaded sensation. She felt a giggle escape her, followed by another. The world seemed suddenly brighter, more vibrant.

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