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).

"Impossible," Emily whispered, her voice barely audible. She'd just finished a grueling pottery class, her hands still stained with clay. The email notification popped up on her phone, and she instinctively recoiled, as if the screen held a venomous snake. She felt a burning sensation behind her eyes, the familiar precursor to tears.

Her ceramics studio, a haven of creative energy, suddenly seemed hostile. The unfinished pots, the scent of damp earth, the dusty sunlight filtering through the windows – everything felt wrong, out of place. She gripped the edge of a pottery wheel, her knuckles turning white, her body trembling with a sudden, uncontrollable shiver. The world around her seemed to tilt and spin.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.324
😰0.323
worse0.301
😖0.294
느껴0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294