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 dusty attic air did little to dampen Chloe’s enthusiasm. Unearthing the time capsule, forgotten and buried in the family home, had ignited a spark within her. Her fingers, stained with grime, carefully lifted the lid. She hummed a little tune, her eyes darting from item to item.

A cassette tape. She recognized the brand. Her hand shook slightly as she reached for it. She found an old tape player. Pressing play, she heard the crackle of static, then a familiar voice. Her own. She'd recorded a message to her future self. Her voice sounded so young, so full of possibilities. A quiet laugh escaped her. This was just what she needed.

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