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 flyer fluttered onto Amelia’s doormat, a beacon of shimmering, hopeful news. "Conversion to Condominiums!" it blared. She snatched it up, the paper crinkling excitedly in her grip. Finally! She’d been waiting for this moment, practically holding her breath.

A manic energy seized her. Amelia raced to the kitchen, tossing open cabinets. Champagne! She needed champagne, and didn’t care what time it was. She pictured the renovations, the sparkling new lobby, the opportunity to finally have a say in her living space.

The cork popped with a satisfying boom, echoing through her apartment. Pouring herself a generous glass, she practically danced back into the living room, a grin splitting her face. She would actually *own* this place. The freedom, the potential… it was all exhilarating.

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