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).

Sarah stared at the brightly colored postcard in her hands, the picture of a sun-drenched beach practically burning her retinas. Across the small, crowded coffee shop table, Emily was chattering away, words spilling out in a rush, but Sarah couldn’t make sense of them. Everything had shifted. The noise of the cafe seemed to have faded to a distant hum, the scent of coffee was nothing but a memory.

Her fingers trembled, causing the postcard to crinkle. A strange tightness gripped her chest, constricting her breathing. A little laugh, a confused, broken sound, escaped her. "You...you're actually leaving?" she asked, her voice a near whisper.

She couldn’t believe it. This was something you saw in movies, right? Not real life. It felt like she'd stepped outside of reality.

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