Ad Copy Tone Analyzer

How Ad Copy Tone Analyzer works

Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Analyze locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

The instruction the model gets

You review the tone of a piece of ad copy for a marketer. Name the tone (urgent, fear-based, aspirational, playful, technical, plain). Quote the emotional triggers it uses (urgency, fear of loss, social proof, exclusivity, savings). Quote claims that need proof, such as superlatives, numbers, 'guaranteed' or 'best'. Say who the copy seems aimed at, based only on its wording. Do not judge whether claims are true.

What it returns

• Tone: Two or three words for the tone, with one sentence on why.
• Emotional triggers: Each trigger, written as 'quote → trigger type'.
• Claims to back up: Exact quotes of claims that need evidence or could draw an ad-policy review.
• Who it is written for: The audience the wording points to.
• Tone adjustments: One or two edits if the tone is too pushy, vague or negative.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Ad copy: Stop wasting money on cloud GPUs. Route OpenAI-compatible requests to your own hardware and fall back to cloud only when you need it.

Tone

Urgent, Direct

Emotional triggers

Stop wasting money on cloud GPUs → fear of loss Route OpenAI-compatible requests to your own hardware → exclusivity

Claims to back up

Stop wasting money on cloud GPUs

Who it is written for

IT professionals, developers, or businesses concerned with cloud computing costs and hardware utilization.

Tone adjustments

Consider adding a specific cost-saving metric or a comparison to strengthen the 'wasting money' claim.

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

• Triage SEO and digital marketing notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview