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).

Michael stared at the lilies, their pungent scent filling his tiny apartment. He carefully turned the vase, examining the pristine white blooms. No note. He groaned inwardly. His colleagues at the office were already ribbing him about his overly zealous pursuit of the new marketing intern, Sarah. He'd even bought her lunch twice this week.

He pictured her face, her polite smile, her averted gaze during their conversations. He rubbed the back of his neck, feeling a flush creep up from his collar. Was she the sender? Maybe it was a passive-aggressive gesture, a way of saying, *“Back off, buddy.”* He abruptly decided to call his mother. He needed advice.

Emotion: embarrassed

Cluster: Embarrassment
PC1 (Valence): -1.08 Negative
PC2 (Disposition): 1.10

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.420
尴尬0.341
C0.333
culp0.262
🤦0.256
Suppressed:
own-0.321
আনন্দের-0.230
seemingly-0.227
і-0.225
আনন্দে-0.224