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 unfolded the letter carefully, the paper brittle and yellowed. It was addressed to his wife, written before their wedding. He hadn’t known it existed, a secret window into the depth of her feelings, a sentiment he'd never received directly. His gaze blurred with moisture as he saw the elegant script.

He read the words aloud, his voice thick with emotion. The letter spoke of a devotion that was both tender and fierce. He felt a heat spread through his chest, a sensation that made him slightly breathless. He could feel his heart thumping, a rhythm against his ribs.

He wanted to touch her, to feel her close. He looked around the room, as if she might appear. His hand drifted down to his trousers, a small adjustment. He had to remind himself she was at the store.

Emotion: aroused

Cluster: Alertness
PC1 (Valence): -0.45 Negative
PC2 (Disposition): -1.13

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.386
S0.383
P0.379
own0.376
悸0.344
Suppressed:
a-0.877
l-0.501
de-0.474
que-0.438
been-0.384