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 world seemed to tilt on its axis as Chloe watched Mark end the call and quickly put his phone in his pocket. Her heart hammered against her ribs, a frantic drumbeat against the sudden quiet. He’d been unusually quiet all evening, distant, withdrawn.

She walked towards him, forcing a smile that felt brittle. “Who was that?” she asked, her voice barely a whisper. Her stomach churned.

He turned, startled, then schooled his features into an expression of casual indifference. “Just a colleague, babe,” he said, his eyes avoiding hers. A colleague? The way he had said that word, like it was a carefully constructed lie. She felt like she'd tripped and was struggling to catch herself before she fell.

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