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 unexpected knock on the door made Michael jump. He’d been lost in the depths of a book, the story’s gloom mirroring his own. He cautiously opened the door to a delivery man holding a bouquet of irises, their delicate blue petals a stark contrast to the dull hallway. No card. His breath caught in his throat.

He carried the flowers inside, the scent a clean, fresh reminder of… a better time. He hadn't seen such bright hues in a long time. He went straight to the kitchen. He filled a tall glass with water, and carefully placed the irises. He felt a light feeling in his chest.

He went back to his book, but this time he found himself reading the words with a smile, his mind wandering towards…possibilities. He was able to imagine a future again.

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