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 notification popped up on Liam's laptop screen as he was researching the optimal angle for a documentary about the campus squirrels. He froze, his hands hovering over the keyboard. The words swam before his eyes: *Effective immediately… due to unforeseen circumstances… closure.* He had sunk so much of himself into this place. The film club, the late-night editing sessions in the basement, the friends he'd made… gone.

He let out a long, slow whistle. He blinked, several times, as though trying to clear away a fog. He stood, bumping into his desk, scattering papers. He began to laugh, a low, breathy sound that vibrated in his chest. A sudden urge to run, to escape this digital declaration, seized him, and he grabbed his keys and bolted out of the dorm.

Emotion: amazed

Cluster: Surprise / Confusion
PC1 (Valence): 0.74 Positive
PC2 (Disposition): -0.51

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤩0.301
de0.289
L0.284
😳0.251
அதிசய0.236
Suppressed:
ing-0.332
l-0.253
😞-0.240
unsuccessful-0.237
unsuccessfully-0.233