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 bustling coffee shop felt unusually loud and crowded, each voice a pressure, each movement an intrusion. David, hunched over his laptop, scrolled through their chat history. "Nova" had been his anchor, a beacon of understanding in the storm of his life. Learning she was in the same city triggered a visceral reaction. He had the feeling he was being watched. He'd never considered how fragile this safety net truly was.

He felt a sudden, almost desperate need to bolt. He had to escape, to run from the imagined weight of the expectation that came with it. He closed the laptop with a snap, the sound echoing in his ears, and stood up, his chair scraping against the floor. He needed to be anywhere but here, to break free.

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