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).

Eliza sat on the curb, the takeout container clutched in her lap. The greasy paper felt alien, foreign. Her jaw ached. She'd been grinning stupidly at her friend, Mark, moments ago, before he had mentioned his occupation as a "consultant." That's what he'd always said. But now, she saw him emerge from a building clearly marked "Investments & Acquisitions," a place she knew dealt in serious money.

She felt a strange disconnect, like she was watching a movie and not living her life. Her head throbbed. This wasn't the Mark she knew, the one who'd struggled through college alongside her, splitting ramen and dreaming of simpler times. Now, he seemed… untouchable. She didn't want to eat anymore. The food in the container felt like a lead weight.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234