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 air in the ballroom seemed to thicken, heavy and suffocating. Sarah pressed her hand to her chest, feeling her pulse thrum erratically against her ribs. The cheerful buzz of conversation, the music, the flashing lights – everything combined to create an unbearable din. She felt like she was trapped in a glass box, watching the world through a distorted lens.

Her carefully applied makeup felt like a mask, and she wanted to claw it off. The thought of small talk made her want to run. She gripped her clutch tightly, her knuckles white.

She saw him, laughing with a group of friends. She turned away.

Emotion: overwhelmed

Cluster: Fear / Anxiety
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -0.94

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.385
😫0.332
😖0.319
😣0.319
😩0.314
Suppressed:
la-0.576
de-0.496
a-0.297
happy-0.290
l-0.264