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).

Eliza’s vision blurred. The shop's dusty display case, usually a source of mundane curiosities, now held something extraordinary. She recognized the intricate filigree, the tiny seed pearls, the way the light danced across the antique emerald at its center. This was her grandmother's ring, a legend in her family. A jolt went through her, her pulse accelerating. "Oh my god," she whispered, the words barely audible.

She felt a sudden urge to laugh, then a prickle of tears behind her eyes. The shop owner, a man with a bored expression, raised an eyebrow. "You like it?" he drawled. Eliza simply nodded, unable to speak, her fingers already reaching out, as if compelled by an unseen force. She had to have it.

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