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 email notification blared, a jarring sound that sliced through the quiet of the office. *Friend request from: Brad Hanson*. Daniel froze, the spreadsheet forgotten. He leaned back in his chair, his gaze fixed on the ceiling. His stomach flipped. He felt like he'd just been punched.

He remembered Brad, the football star, the undisputed king of the school. The one who had made Daniel's life a living hell. He started to laugh, a short, sharp bark of disbelief. Then he closed his eyes and took a deep breath. His palms were clammy. This was… unexpected.

He finally opened the email and viewed Brad's profile. The smiling face felt like a challenge. He clicked accept. This was going to be interesting.

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