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).

"Excuse me, are you Mr. Davies?" The voice, sharp and precise, belonged to Mrs. Hawthorne, a woman who always seemed to carry an air of judgment. She was rarely seen outdoors. Today, however, she stood on his doorstep, the picture of refined composure, a small, uncharacteristic smile playing on her lips.

"Yes?" Mr. Davies replied, completely thrown by her presence.

"Regarding the elm… the one dividing our properties…" she began, her voice taking on a strangely hesitant tone. "I've been… considering… would you object to its removal?" Mr. Davies felt a sudden warmth spread through his chest. He blinked repeatedly, trying to clear the fog from his brain. The world seemed to have shifted on its axis. He felt a sudden, inexplicable lightness.

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