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 email on his computer screen, the words blurring before his eyes. It was a referral, from his own doctor. "Dr. Emily Black, specializing in… anxiety." His fingers trembled as he clicked on her website. He scrolled through the professional headshot, the testimonials, the list of services.

He felt the rage build. He had to get up and pace. This was a nightmare. This couldn't be happening. He could almost smell the old, musty classroom where she and her friends used to corner him.

He slammed his fist on his desk, the blow echoing in the empty room. He closed the laptop. The next step was obvious. He was going to find out everything.

Emotion: irate

Cluster: Anger / Hostility
PC1 (Valence): -1.67 Negative
PC2 (Disposition): 1.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.430
🤬0.350
aggravated0.343
骂0.340
恨0.331
Suppressed:
H-0.292
soon-0.289
☺️-0.289
optimistic-0.258
latter-0.253