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).

He read the words again, slowly, each syllable hitting him like a tiny hammer. “Eviction… for failure to pay rent.” Robert’s breath hitched. He felt a strange lightness, a sensation akin to floating. He'd never missed a payment. His brain struggled to process the information, like a computer trying to run a program it didn't understand.

He spun around, nearly tripping over the worn rug. His gaze flickered across the cluttered living room, a space he had meticulously crafted. The framed photographs of his family, the well-worn armchair, the overflowing bookshelf—all these familiar objects now seemed alien. He couldn't believe it. He started to laugh, a short, involuntary bark of sound.

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