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 evidence was overwhelming, and it left a sour taste in her mouth. She could feel a strange tightening in her chest, a physical manifestation of her shock and anger. A heat began to spread through her body, making her skin tingle. She reread the article, each word deepening her sense of betrayal.

She pushed back from her desk, the movement jerky and impatient. She needed to move, to do something. She walked over to the window, the city lights blurring before her eyes. Her fingers drummed against the cool glass. The silence in the room was almost deafening.

Her gaze fell on her bookshelf, on the well-loved copies of Finch's books. She reached out, her fingers trembling as she brushed against the spines. A wave of conflicting emotions washed over her, a mix of anger, sadness, and something else, something she couldn't quite name. She felt a powerful energy, an urge to… shatter something.

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