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 stared, mouth agape, at the riot of color spilling from the vase on his desk. Crimson roses, delicate freesia, a hint of blue forget-me-nots – a masterpiece. No card. Just…flowers. He ran a hand through his already disheveled hair, completely flummoxed.

This wasn't his usual Tuesday. His usual Tuesday involved lukewarm coffee, a mountain of paperwork, and the crushing weight of deadlines. The flowers were…otherworldly.

He picked up a rose, inhaled deeply, and something within him unfurled. His tight shoulders loosened. A smile tugged at the corners of his lips. He sat back in his chair, a sense of something…new, bubbling inside him. He felt strangely…buoyant.

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