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 archaeologist, Dr. Anya Sharma, felt a tremor run through her. The time capsule, unearthed during a routine dig, held a trove of artifacts that defied all expectations. This was not the historical period they'd been investigating. The items within – a sleek, silver device and a collection of crystalline objects – hinted at a civilization she'd only read about in speculative fiction. She ran a hand through her hair, her gaze locked on the peculiar contents.

She barked orders, her voice sharper than usual, directing her team to document every detail. She knew that what she was holding was significant, a revelation, something that would rewrite the history books. She grabbed a notebook and began furiously scribbling, her pen a blur across the page.

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