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).

John whistled as he logged into the account, his heart giving a little flutter in his chest. A sizeable amount stared back at him, the result of years of quiet planning from Mary. He felt a sudden, giddy lightness. He pictured the renovations they'd discussed, the ones they'd shelved because of budget constraints.

He imagined the newly renovated kitchen, finally perfect for baking with the grandchildren. A genuine laugh bubbled up from him. He scrolled through the transactions, a wave of affection washing over him for his practical, forward-thinking wife.

"Well, Mary," he muttered to himself, "Looks like we're finally getting that island." He immediately texted her a picture of the balance, then began researching kitchen designs.

Emotion: hopeful

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): -0.58

Role in Research

This story is one of 1,000 stories generated for the emotion hopeful. 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 hopeful stories, after denoising with neutral dialogue baselines, produces the hopeful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the hopeful vector is projected through the unembedding matrix.

Promoted:
de0.715
la0.549
B0.468
🀩0.452
enthusi0.433
Suppressed:
S-0.603
不-0.401
😞-0.399
worse-0.394
C-0.386