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 silence in the library was broken only by the frantic tapping of keyboards and the hushed whispers of students. Olivia sat at a computer, unable to concentrate. Her fingers fumbled over the keys, each click a painful reminder of the impending closure.

She felt as if the world was tilting on its axis. All her carefully laid plans, her dreams for the future – they were all in jeopardy. The university, her sanctuary, her safe haven, was about to disappear.

She took a deep breath, trying to regain control, but the anger inside her was a raging fire. She pushed away from her desk, her chair scraping against the floor, and marched out of the library, the abruptness of her movement disrupting the stillness.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
恨0.334
🤬0.327
aggravated0.323
骂0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260