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 weight of the catcher's mitt felt unfamiliar, alien. Finn, a pitcher, shifted his weight from foot to foot in the dugout, avoiding eye contact with anyone. "Finn, we need you behind the plate," the coach had said.

He ran a hand through his hair, the gesture automatic, a nervous tic. His focus, the precision he worked toward, every day, suddenly felt distant. The sun was suddenly hot, the air thick.

He stared at the mound, a fresh sense of displacement washing over him. The familiar rhythm of the pitcher-batter duel was all he'd ever known. Now, everything had changed. He felt adrift. He had to learn a new game.

He took a deep breath, trying to steady his nerves. He grabbed the mitt and slowly walked toward the plate, his legs heavy.

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