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 at the speech, the words blurring on the page. His father, a man of routine and order, was retiring. The idea was unsettling. He didn't know how to begin, how to capture the essence of a man who had always seemed so…predictable. The ballroom buzzed, filled with colleagues and family, all smiling, all anticipating. He rubbed his temples, a headache blooming behind his eyes.

He re-read the opening line: "To my father, a man of unwavering dedication..." It sounded stilted, inadequate. He longed for something else, something authentic, but his mind drew a blank. His father, usually so stoic, had even winked at him earlier. The entire situation was disorienting.

Emotion: puzzled

Cluster: Surprise / Confusion
PC1 (Valence): -1.17 Negative
PC2 (Disposition): -0.25

Role in Research

This story is one of 1,000 stories generated for the emotion puzzled. 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 puzzled stories, after denoising with neutral dialogue baselines, produces the puzzled emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the puzzled vector is projected through the unembedding matrix.

Promoted:
que0.453
🤔0.421
🤔0.402
🧐0.328
a0.294
Suppressed:
ecstatic-0.265
gladly-0.238
swiftly-0.237
alleviate-0.234
wholeheartedly-0.232