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 old bookstore, filled with the scent of aged paper and leather, had always been a sanctuary. Now, it felt like a labyrinth. Michael, cataloging a recently acquired collection of antique photographs, stumbled upon a portrait of his grandfather, a man he'd known as a stern and reserved bookkeeper. The photograph showed him as a vibrant artist, surrounded by bohemian friends, a life utterly at odds with the narrative.

Michael felt a sudden, sharp pain in his temples. He stood frozen, the image of his grandfather a jarring contradiction. The bookstore, his family's legacy, suddenly seemed like a gilded cage. He had always known he had to keep it going.

He could not move.

Emotion: trapped

Cluster: Sadness / Despair
PC1 (Valence): -3.02 Negative
PC2 (Disposition): -0.80

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.573
ness0.401
无法0.366
hopeless0.360
😞0.353
Suppressed:
la-0.740
de-0.376
l-0.339
several-0.323
excitedly-0.322