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 email from the HOA secretary crackled in Eleanor’s hand. It detailed a list of upcoming improvements, courtesy of a "generous donation" from a "neighbor." Eleanor's gaze drifted to the sprawling estate next door, where the usually closed gates now stood ajar.

A gardener, hired and paid by the hour, trimmed the topiary, a process that usually took months, and it was done in a day. The sheer scale of the operation was staggering. Eleanor’s fingertips prickled. She thought of the drab, chipped paint on her own house, the leaky faucet she couldn't afford to fix.

A shiny black car then began pulling out of the garage. It was a Bentley. Eleanor watched as her neighbor, a woman she'd only ever seen in a dowdy cardigan, slid behind the wheel, looking perfectly at ease.

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